© 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. 10287
    Prev
    Next
    INDEX
    Explanations

    ratio

    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
    andone
    -0.06
    arne
    -0.06
     Bod
    -0.06
    åıĮåŁİ
    -0.06
    ç¼Ī
    -0.06
     Grass
    -0.06
     icon
    -0.06
    arsing
    -0.06
    rane
    -0.06
    ä½įæķ°
    -0.06
    POSITIVE LOGITS
    .policy
    0.08
    éĸ¢ä¿ĤãĤĴ
    0.08
    ׳×Ļ×ķת
    0.08
    odat
    0.08
    μαÏĦο
    0.07
    _ratio
    0.07
    濯
    0.07
    æĢ»æ¯Ķ
    0.07
    Ratio
    0.07
    åįłæĢ»
    0.07
    Activations Density 0.003%

    No Known Activations