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. 131012
    Prev
    Next
    INDEX
    Explanations

    Mil

    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
     Props
    -0.08
    eut
    -0.08
     أج
    -0.07
    材质
    -0.07
    bec
    -0.07
    这样的
    -0.07
    _probs
    -0.07
    ありますが
    -0.07
     bul
    -0.06
    十年前
    -0.06
    POSITIVE LOGITS
    ძ
    0.08
     terre
    0.07
    .�
    0.07
     oracle
    0.07
     murder
    0.07
     Word
    0.07
    冕
    0.07
     switch
    0.07
    永利
    0.07
     victory
    0.07
    Activations Density 0.002%

    No Known Activations