© 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. 55451
    Prev
    Next
    INDEX
    Explanations

    acrylamide and methacrylates

    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
    ustr
    -0.07
    åĨĮ
    -0.06
    kill
    -0.06
    /out
    -0.06
    Wr
    -0.06
    -path
    -0.06
    esModule
    -0.06
    acing
    -0.06
    庸
    -0.06
    _GUID
    -0.06
    POSITIVE LOGITS
    icken
    0.08
    airo
    0.08
    inate
    0.08
    _GRE
    0.08
     cocos
    0.08
    大çİĭ
    0.08
    ylene
    0.08
    amura
    0.08
     tóc
    0.08
    ashian
    0.08
    Activations Density 0.053%

    No Known Activations