© 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. 7967
    Prev
    Next
    INDEX
    Explanations

    ice with punctuation

    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
    èĤĩ
    -0.07
    è¿ĻæĦıåij³çĿĢ
    -0.07
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.07
    جÙĬر
    -0.06
    åľ¨åħ¶
    -0.06
    æľī以ä¸ĭ
    -0.06
    å½Ŀ
    -0.06
     med
    -0.06
    夫åIJĽ
    -0.06
    DEL
    -0.06
    POSITIVE LOGITS
    bey
    0.08
     Voi
    0.08
    dsa
    0.08
    ÅŁam
    0.08
    anyol
    0.08
    åĭĻ
    0.07
    /ros
    0.07
    iggins
    0.07
    ActivityResult
    0.07
    ties
    0.07
    Activations Density 0.042%

    No Known Activations