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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 3264
    Prev
    Next
    INDEX
    Explanations

    in

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roy
    -0.07
    圃
    -0.07
     TRANSACTION
    -0.07
     në
    -0.07
    ㅤ
    -0.06
     Surely
    -0.06
    펼
    -0.06
     hız
    -0.06
    פר
    -0.06
    污泥
    -0.06
    POSITIVE LOGITS
    message
    0.09
    dictions
    0.08
    	board
    0.07
    shima
    0.07
    present
    0.07
    (des
    0.07
    Stored
    0.07
    小
    0.07
     mil
    0.06
    蔫
    0.06
    Activations Density 0.002%

    No Known Activations