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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23-RESID-POST-AA
    11. 454
    Prev
    Next
    INDEX
    Explanations

    please

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mat
    -0.07
    �
    -0.07
     fixed
    -0.07
     receipt
    -0.07
    orean
    -0.07
    無い
    -0.07
     double
    -0.07
    Morning
    -0.07
     vested
    -0.07
    	vm
    -0.07
    POSITIVE LOGITS
    aaa
    0.07
    ᴉ
    0.07
    걷
    0.07
     navCtrl
    0.07
    -fields
    0.06
    ｩ
    0.06
     בארץ
    0.06
    .loadData
    0.06
     [.
    0.06
    acas
    0.06
    Activations Density 0.000%

    No Known Activations