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. 131054
    Prev
    Next
    INDEX
    Explanations

    Bes

    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
     Kre
    -0.08
    에너
    -0.07
     attenuation
    -0.07
     innate
    -0.07
    多位
    -0.07
    落叶
    -0.07
    会不会
    -0.07
    .ToInt
    -0.07
    ⁈
    -0.07
    reib
    -0.07
    POSITIVE LOGITS
    okers
    0.07
     Eventually
    0.07
     Consulting
    0.07
     channelId
    0.07
     Contractors
    0.07
     passengers
    0.06
    parcel
    0.06
     bends
    0.06
    這樣
    0.06
     man
    0.06
    Activations Density 0.000%

    No Known Activations