© 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. 61547
    Prev
    Next
    INDEX
    Explanations

    exact details or specific proposals

    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
    ovas
    -0.08
    纵è§Ĥ
    -0.08
     rightfully
    -0.08
    éĢĤå½ĵ
    -0.07
    æľĢç»Ī以
    -0.07
     Moo
    -0.07
    æĺ¯åIJ¦èĥ½å¤Ł
    -0.07
     algemeen
    -0.07
     general
    -0.07
    缴è¾ĸ
    -0.07
    POSITIVE LOGITS
    åħ·ä½ĵçļĦ
    0.07
    reb
    0.07
    ç»ĨèĬĤ
    0.07
    èĵī
    0.07
    ukur
    0.06
    ément
    0.06
     Specifically
    0.06
     Cyr
    0.06
    åIJijæĹ¥
    0.06
    åħ·é«Ķ
    0.06
    Activations Density 0.021%

    No Known Activations