© 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. 37854
    Prev
    Next
    INDEX
    Explanations

    pre-filled, pre-populates

    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
    åįģç«ł
    -0.07
    cka
    -0.07
    eren
    -0.07
     Parkway
    -0.07
    åħ³æ³¨
    -0.07
    é¢Ĩ
    -0.07
    ãģ«éĸ¢ãģĹãģ¦
    -0.06
    大æ¦Ĥå°±æĺ¯
    -0.06
    sdale
    -0.06
    èĢģçļĦ
    -0.06
    POSITIVE LOGITS
    ÃŃss
    0.07
    åħĭåħ°
    0.06
    irit
    0.06
    odesk
    0.06
    <|repo_name|>
    0.06
    èĸªæ°´
    0.06
    转载èĩ³
    0.06
     zaÅĽ
    0.06
    alani
    0.06
    omie
    0.06
    Activations Density 0.053%

    No Known Activations