© 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. 45902
    Prev
    Next
    INDEX
    Explanations

    worth considering / need / deserve

    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
    enne
    -0.08
    濯
    -0.08
    nod
    -0.07
    ificare
    -0.07
    voz
    -0.07
    èĬĿ
    -0.07
    tai
    -0.07
    æĬĵåĪ°
    -0.07
    enheim
    -0.07
    çŃĶéģĵ
    -0.07
    POSITIVE LOGITS
    为ä»Ģä¹Īè¦ģ
    0.09
    è¿Ļä¹Īåģļ
    0.08
    ister
    0.08
    ceed
    0.08
    æѤç§į
    0.08
    /use
    0.08
    éĥ½åĢ¼å¾Ĺ
    0.08
     worth
    0.07
     reconsider
    0.07
    ä¸įåĢ¼å¾Ĺ
    0.07
    Activations Density 0.272%

    No Known Activations