© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57177
    Prev
    Next
    INDEX
    Explanations

    how to access

    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
    çĶ¨æĪ·ä¸Ĭä¼ł
    -0.09
    Uploaded
    -0.08
    ÙĦز
    -0.08
    ä¸Ĭä¼łèĢħ
    -0.08
    lfw
    -0.08
     Uploaded
    -0.08
    æīĭæľºéĺħ读
    -0.08
    Jvm
    -0.08
     rodada
    -0.08
    _uploaded
    -0.07
    POSITIVE LOGITS
    access
    0.09
    æĵįä½ľæŃ¥éª¤
    0.08
     Access
    0.08
    æīĭéłĨ
    0.08
     access
    0.08
    Access
    0.08
    æĵįä½ľ
    0.07
     menu
    0.07
    访éĹ®
    0.07
     procedure
    0.07
    Activations Density 0.617%

    No Known Activations