© 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. 26737
    Prev
    Next
    INDEX
    Explanations

    numbers followed by comma or underscore

    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
    zne
    -0.07
    .innerHeight
    -0.06
    两ä¸į误
    -0.06
    à®ķà¯ģ
    -0.06
    éļ¾æ±Ĥ
    -0.06
    ×ķ×¢
    -0.06
    俩人
    -0.06
     Tew
    -0.06
    ington
    -0.06
    unate
    -0.06
    POSITIVE LOGITS
    è¡Įä¹ĭ
    0.08
    ä¸įåĪĨ
    0.08
    ooks
    0.08
    icona
    0.07
    ÏĩÏģο
    0.07
    âĨ³
    0.07
    andid
    0.07
    _invoke
    0.07
    èĥ¤
    0.07
    íķŃ
    0.07
    Activations Density 0.035%

    No Known Activations