© 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. 60979
    Prev
    Next
    INDEX
    Explanations

    dependency or library reference

    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
    umen
    -0.07
    adz
    -0.07
    å¸ĥä»Ģ
    -0.06
    ibel
    -0.06
    oney
    -0.06
     inter
    -0.06
    /www
    -0.06
    .constructor
    -0.06
    ASA
    -0.06
    uft
    -0.06
    POSITIVE LOGITS
    starter
    0.08
    exe
    0.07
     Torn
    0.07
    è´§åı·
    0.07
    åľ¨çº¿æŶéĹ´
    0.07
    WithName
    0.07
     fenced
    0.07
     подклÑİÑĩа
    0.07
    Æ°
    0.07
    icipant
    0.07
    Activations Density 0.230%

    No Known Activations