© 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. 8308
    Prev
    Next
    INDEX
    Explanations

    Hall effect

    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
    amenta
    -0.08
    ONGO
    -0.08
    ESIS
    -0.07
    zlich
    -0.07
    sein
    -0.07
    aeda
    -0.07
    åįļæł¼
    -0.07
    æľªåıĸå¾Ĺ
    -0.07
     Shr
    -0.07
    夫æĸ¯åŁº
    -0.07
    POSITIVE LOGITS
    ydd
    0.08
    boarding
    0.08
    çŁ¥è§ī
    0.07
    åĬĽå¼º
    0.07
     embedding
    0.07
    妥
    0.07
    æľĢ强çļĦ
    0.07
    craft
    0.07
    亲åĴĮåĬĽ
    0.07
    å¾Ī强çļĦ
    0.07
    Activations Density 0.002%

    No Known Activations