© 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. 31682
    Prev
    Next
    INDEX
    Explanations

    names after `Her`

    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
    æ¡ĥæĿİ
    -0.07
     ug
    -0.07
    éĻį级
    -0.07
    ellini
    -0.07
    oplevel
    -0.07
    榴
    -0.07
     Nest
    -0.07
    aghetti
    -0.06
    赤
    -0.06
    ugn
    -0.06
    POSITIVE LOGITS
    夥
    0.08
    .parallel
    0.08
    éĿ¶
    0.07
     QUERY
    0.07
    -vector
    0.07
    oracle
    0.07
    ehold
    0.07
     quantum
    0.07
    æ£Ģç´¢
    0.07
     HASH
    0.07
    Activations Density 0.009%

    No Known Activations