© 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. 27860
    Prev
    Next
    INDEX
    Explanations

    enhance / enhancement / improving

    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
    æĪijæĿ¥è¯´
    -0.09
    -0.08
    ation
    -0.08
    chy
    -0.08
    å§ĭèĩ³ç»Ī
    -0.07
    ãģ¾ãģ¾
    -0.07
    ãģĵãĤį
    -0.07
    人æĿ¥è¯´
    -0.07
    intis
    -0.07
    olini
    -0.07
    POSITIVE LOGITS
    ments
    0.13
    ancement
    0.11
    anced
    0.10
    /disable
    0.10
    ancements
    0.10
    bourg
    0.09
    ometown
    0.09
    jenigen
    0.08
    åī¤
    0.08
    åĬij
    0.08
    Activations Density 0.025%

    No Known Activations