© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22137
    Prev
    Next
    INDEX
    Explanations

    XML descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estens
    -0.08
    erness
    -0.08
    iums
    -0.08
    bra
    -0.08
    ecke
    -0.08
    ocken
    -0.08
    ç¾İå¦Ļ
    -0.07
    ë¦Ń
    -0.07
    anyi
    -0.07
    aston
    -0.07
    POSITIVE LOGITS
     xlink
    0.07
    æ®´
    0.07
    maa
    0.06
    pon
    0.06
    maids
    0.06
    _pub
    0.06
    OT
    0.06
     initials
    0.06
    rech
    0.06
    dehyde
    0.06
    Activations Density 0.001%

    No Known Activations