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. 131064
    Prev
    Next
    INDEX
    Explanations

    Step

    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
    okers
    -0.07
    phants
    -0.07
     binge
    -0.07
     rightfully
    -0.07
    芋
    -0.07
    Discover
    -0.07
    となり
    -0.07
    .spy
    -0.07
    encer
    -0.07
    _SSL
    -0.07
    POSITIVE LOGITS
    rw
    0.08
     giorni
    0.08
     página
    0.08
     frase
    0.08
    HandlerContext
    0.07
    ضة
    0.07
    ellido
    0.07
     →
    0.07
    Ƞ
    0.07
     Version
    0.06
    Activations Density 0.017%

    No Known Activations