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. 130989
    Prev
    Next
    INDEX
    Explanations

    Foreign words/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
    .dim
    -0.07
    启迪
    -0.07
    Ln
    -0.07
    REM
    -0.07
    首个
    -0.06
    隐蔽
    -0.06
    وحدة
    -0.06
    >'.↵
    -0.06
     logistics
    -0.06
    眸
    -0.06
    POSITIVE LOGITS
    שואה
    0.07
    Accordion
    0.07
    -fontawesome
    0.07
     הישראלי
    0.07
    .ViewHolder
    0.07
    _OLD
    0.06
    ột
    0.06
     viewModel
    0.06
    工艺品
    0.06
    rcode
    0.06
    Activations Density 0.000%

    No Known Activations