© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37467
    Prev
    Next
    INDEX
    Explanations

    the present invention

    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
    Negative Logits
    å¤Ħå¤Ħ
    -0.08
    çĥ¬
    -0.08
     entirety
    -0.07
    oen
    -0.07
    oke
    -0.07
    osen
    -0.07
    ork
    -0.07
    .serial
    -0.07
    身影
    -0.06
    Barrier
    -0.06
    POSITIVE LOGITS
    ucker
    0.08
    _plural
    0.07
    æĭIJ弯
    0.07
    çµĨ
    0.07
    formatter
    0.07
    繫
    0.07
    修饰
    0.07
    ç³»
    0.07
     Ñģклон
    0.07
     cand
    0.07
    Activations Density 0.043%

    No Known Activations