© 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. 38713
    Prev
    Next
    INDEX
    Explanations

    technical specifications and programming

    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
    ead
    -0.07
    åĴ¸
    -0.07
    对åħ¶çľŁå®ŀæĢ§è´Łè´£
    -0.07
    é¹¹
    -0.06
    kee
    -0.06
    Ñīи
    -0.06
    ä¸įæķ£
    -0.06
    ROID
    -0.06
     perce
    -0.06
    çŃij
    -0.06
    POSITIVE LOGITS
    åıįå¤į
    0.08
    æľĢæĸ°è¯Ħ论
    0.08
    indh
    0.08
    æĽ´æĸ°èĩ³
    0.07
    //
    0.07
    UTO
    0.07
    tracker
    0.07
    åħĭç½Ĺ
    0.07
    _USB
    0.07
    aintenance
    0.07
    Activations Density 0.001%

    No Known Activations