© 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. 8614
    Prev
    Next
    INDEX
    Explanations

    probability of picking

    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
    afe
    -0.08
    ë¦Ħ
    -0.08
    tol
    -0.08
    ä¼ĺèī¯çļĦ
    -0.08
    容å¿į
    -0.07
    ä¸įèĥ½åľ¨
    -0.07
    ToMany
    -0.07
    大èĩ´
    -0.07
    Queryable
    -0.07
    appable
    -0.07
    POSITIVE LOGITS
    è¿ĻæŃ£æĺ¯
    0.10
    ç§Ģ
    0.08
    hots
    0.08
     proof
    0.08
    è¯ģ
    0.07
    èĥ½å¤Łè¾¾åĪ°
    0.07
    è¯ģæĺİ
    0.07
    definitions
    0.07
    æ·±æľī
    0.07
    çļĦè¯ģæĺİ
    0.07
    Activations Density 0.005%

    No Known Activations