© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26849
    Prev
    Next
    INDEX
    Explanations

    necessary and requirement

    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
    manship
    -0.10
    sgi
    -0.10
    orners
    -0.09
    ìį¨
    -0.09
    pery
    -0.09
    ectes
    -0.09
    agher
    -0.09
    alise
    -0.09
    regor
    -0.09
    ساÙĩÙħ
    -0.09
    POSITIVE LOGITS
    ä¸įåı¯æ¬ł
    0.10
    -looking
    0.09
    itating
    0.08
    itated
    0.08
    itates
    0.08
    es
    0.07
    eva
    0.07
    at
    0.07
    ioned
    0.07
    lv
    0.07
    Activations Density 0.016%

    No Known Activations