© 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. 12626
    Prev
    Next
    INDEX
    Explanations

    AndGet OrUpdate

    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
    a
    -0.09
    auss
    -0.08
    vertime
    -0.08
     ìĿ¸íķľ
    -0.07
    sterreich
    -0.07
    sl
    -0.07
    sWith
    -0.07
    ob
    -0.07
    n
    -0.06
    ed
    -0.06
    POSITIVE LOGITS
    AndGet
    0.10
    <|box_end|>
    0.10
    Æ°á»Ľt
    0.10
    endiri
    0.09
    OrUpdate
    0.09
    νοÏį
    0.09
    ÑĢод
    0.09
    utom
    0.09
    rÅijl
    0.09
    quÃŃ
    0.09
    Activations Density 0.132%

    No Known Activations