© 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. 21401
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     detriment
    -0.07
    ToLower
    -0.07
    æĬ±æĬ±
    -0.06
     Madr
    -0.06
    odle
    -0.06
    åĽ¤
    -0.06
    ä¼ĺèĥľ
    -0.06
    haj
    -0.06
    è¢ĸåŃIJ
    -0.06
    åĶı
    -0.06
    POSITIVE LOGITS
    çĹħæĥħåĪĨæŀIJ
    0.07
    isible
    0.07
    _INLINE
    0.07
    водов
    0.07
    зÑĢа
    0.07
    ilet
    0.07
    _locked
    0.07
    berman
    0.07
    iop
    0.07
    ideo
    0.07
    Activations Density 0.000%

    No Known Activations