© 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. 69245
    Prev
    Next
    INDEX
    Explanations

    say processing stages

    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
     registro
    -0.08
    inscription
    -0.07
     --------------------
    -0.07
     הייתי
    -0.07
    productId
    -0.07
    ("----------------
    -0.07
     »,
    -0.07
    dependence
    -0.07
     Gratuit
    -0.07
    إصلاح
    -0.07
    POSITIVE LOGITS
    乙方
    0.07
    NK
    0.07
     workstation
    0.07
    ilers
    0.07
    뎟
    0.06
     cipher
    0.06
    .workflow
    0.06
    ﾉ
    0.06
    �
    0.06
    源
    0.06
    Activations Density 0.039%

    No Known Activations