© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7210
    Prev
    Next
    INDEX
    Explanations

    state abbreviations, survey released, user ID

    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¶Ľ
    -0.07
    azionale
    -0.07
    verstanden
    -0.06
    认æ¸ħ
    -0.06
    ohn
    -0.06
    ç½®
    -0.06
    éĺħ
    -0.06
    eneg
    -0.06
    è´§
    -0.06
    gor
    -0.06
    POSITIVE LOGITS
    apan
    0.09
    جد
    0.08
    [in
    0.08
    <Cell
    0.08
    ftime
    0.08
    wej
    0.08
    _MIX
    0.08
    InitStruct
    0.08
    ALSE
    0.07
    tempts
    0.07
    Activations Density 0.002%

    No Known Activations