© 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. 43932
    Prev
    Next
    INDEX
    Explanations

    undefined variable, index, method, behavior, symbol

    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
    çģ¿çģ¿
    -0.08
    asename
    -0.08
    oure
    -0.08
    æĨ¬
    -0.07
    chester
    -0.07
     Bosco
    -0.07
    оÑĢод
    -0.07
    (:,:,
    -0.07
    drawable
    -0.07
    Ñĩа
    -0.07
    POSITIVE LOGITS
    å¼ķ人åħ¥
    0.07
     unresolved
    0.07
    å½¢å¼ıçļĦ
    0.06
    è¿ĻäºĽéĹ®é¢ĺ
    0.06
    å¢ĥåľ°
    0.06
     íĺķíĥľìĿĺ
    0.06
    ä¸ŃçļĦä¸Ģç§į
    0.06
     Tate
    0.06
    etype
    0.06
     calculus
    0.06
    Activations Density 0.003%

    No Known Activations