© 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. 47646
    Prev
    Next
    INDEX
    Explanations

    actual / cannot

    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
    /octet
    -0.08
    taal
    -0.08
    .BO
    -0.07
    zac
    -0.07
    izas
    -0.07
    екÑģи
    -0.07
    lassian
    -0.06
    _hint
    -0.06
    achel
    -0.06
    紧紧
    -0.06
    POSITIVE LOGITS
     actual
    0.09
    actual
    0.09
    å®ŀéĻħ
    0.08
    å®ŀéĻħæĵįä½ľ
    0.08
    ä½Ĩåı¯ä»¥
    0.08
    GRAPH
    0.07
     actually
    0.07
    å®ŁéļĽãģ«
    0.07
    å®ŁéļĽ
    0.07
    ä¸įèĥ½åľ¨
    0.07
    Activations Density 0.027%

    No Known Activations