© 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. 13482
    Prev
    Next
    INDEX
    Explanations

    lists of things

    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
    avs
    -0.08
    /mat
    -0.07
     NGH
    -0.07
     веÑīе
    -0.07
    çĥ½
    -0.07
    çł¥
    -0.07
    ë¶Ģ
    -0.07
    mata
    -0.06
    ARRY
    -0.06
    /Register
    -0.06
    POSITIVE LOGITS
    代ä¹ĭ
    0.07
    è¿Ļæł·åģļ
    0.06
    _ELEMENTS
    0.06
    ÙĬÙģ
    0.06
    anno
    0.06
    æ¯
    0.06
    óry
    0.06
    acad
    0.06
    ä¹ĭåĬĽ
    0.06
    ited
    0.06
    Activations Density 0.121%

    No Known Activations