© 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. 31942
    Prev
    Next
    INDEX
    Explanations

    statistics, fat, library, at

    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
    ä¸Ģæĸ¹éĿ¢
    -0.08
    uç
    -0.07
     obv
    -0.07
    reto
    -0.07
    å·¥ä½ľæĬ¥åijĬ
    -0.07
    elay
    -0.06
    _IDENTIFIER
    -0.06
    åħ¶ä»ĸ类似éĹ®é¢ĺ
    -0.06
    upe
    -0.06
    æĸ½
    -0.06
    POSITIVE LOGITS
    $:
    0.07
    ãģĤãģı
    0.07
    ":
    0.07
    »:
    0.07
    é´»
    0.07
    )":
    0.07
    `:
    0.07
    ori
    0.07
    涼
    0.07
     restless
    0.07
    Activations Density 0.068%

    No Known Activations