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. 131032
    Prev
    Next
    INDEX
    Explanations

    say "em" words

    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
    齿轮
    -0.08
    intendent
    -0.07
    arden
    -0.07
    inely
    -0.07
    ourcem
    -0.07
    _PLAY
    -0.07
     mum
    -0.06
    酷
    -0.06
    FOR
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    _cookies
    0.07
    相应的
    0.07
     warranties
    0.07
     option
    0.07
     صلى
    0.07
     requested
    0.07
    하다
    0.07
    -extra
    0.07
     reconcile
    0.07
     undesirable
    0.07
    Activations Density 0.001%

    No Known Activations