Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 131017
    Prev
    Next
    INDEX
    Explanations

    Other languages/code

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Similarly
    -0.07
     slag
    -0.07
    と共
    -0.07
    =default
    -0.07
    סמוך
    -0.07
     ].
    -0.07
     '';
    -0.07
    remaining
    -0.07
     Stark
    -0.07
    ']).
    -0.07
    POSITIVE LOGITS
     day
    0.07
     cz
    0.07
    ゾ
    0.06
     vids
    0.06
    键
    0.06
    aments
    0.06
    饶
    0.06
    早
    0.06
     vive
    0.06
    �
    0.06
    Activations Density 0.000%

    No Known Activations