© 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 EvalsExportsinterp-engineNEWAPI 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. 120446
    Prev
    Next
    INDEX
    Explanations

    Database connection strings

    np_max-act · gemini-2.0-flash
    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
    .cleanup
    -0.07
    蝮
    -0.07
    textInput
    -0.07
     key
    -0.07
    津
    -0.07
     הנתבע
    -0.06
    殣
    -0.06
    焉
    -0.06
    麇
    -0.06
     Gast
    -0.06
    POSITIVE LOGITS
    players
    0.07
    (pref
    0.07
    (arc
    0.07
     toujours
    0.07
    _total
    0.07
    썹
    0.07
    抚摸
    0.07
    	for
    0.07
    APPLE
    0.07
    เผย
    0.07
    Activations Density 0.002%

    No Known Activations