© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 51534
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron detects the infinitival marker that introduces verbs (the "to" that begins infinitive/ purpose verb phrases).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hong
    -0.07
     tej
    -0.07
     توف
    -0.06
    推测
    -0.06
     harming
    -0.06
    萌
    -0.06
     defined
    -0.06
     Bram
    -0.06
    ..↵
    -0.06
    RAP
    -0.06
    POSITIVE LOGITS
    €™
    0.07
    ・・
    0.07
     workplace
    0.07
    	SET
    0.07
    .Buffer
    0.07
     Fälle
    0.07
     eventdata
    0.07
     Molecular
    0.06
    -bordered
    0.06
     Bü
    0.06
    Activations Density 0.833%

    No Known Activations