© 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. 62307
    Prev
    Next
    INDEX
    Explanations

    two classes or divisions

    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
    åħĭåħ°
    -0.09
    éĥ½ä¸įä¸Ģæł·
    -0.08
    omor
    -0.07
    ÑĪÑĤей
    -0.07
    veral
    -0.07
    å½¢å¼ıå¤ļæł·çļĦ
    -0.07
    ÙĪاع
    -0.07
    ehm
    -0.07
    ä½ıè¡Į
    -0.07
    etc
    -0.07
    POSITIVE LOGITS
    ä¸Ģç§įæĺ¯
    0.09
     íķĺëĤĺëĬĶ
    0.07
    ä¸Ģ个æĺ¯
    0.07
    ä»İåīį
    0.07
    ä¸ĢåįĬ
    0.06
    åįĹå±±
    0.06
    è¹´
    0.06
    ä¸Ģæĺ¯
    0.06
    åį³
    0.06
    ä¸Ģéĥ¨åĪĨ
    0.06
    Activations Density 0.155%

    No Known Activations