© 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. 44036
    Prev
    Next
    INDEX
    Explanations

    primary key

    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
    roc
    -0.08
    lvl
    -0.08
    ä¸½å¨ľ
    -0.07
    æģ©
    -0.07
    _OCC
    -0.07
    -tools
    -0.07
    βάλ
    -0.07
    strup
    -0.07
    _unix
    -0.07
    ÑĢиз
    -0.07
    POSITIVE LOGITS
    uzzi
    0.08
    ekar
    0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
    æĢ§éĹ®é¢ĺ
    0.07
    æł¹æį®ä¸ªäºº
    0.07
    udas
    0.06
    ä¹ĭæĹ¥
    0.06
    oger
    0.06
    ä¸ĭè¿°
    0.06
     Arquit
    0.06
    Activations Density 0.390%

    No Known Activations