© 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. 47906
    Prev
    Next
    INDEX
    Explanations

    substance names and types

    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
    举éĺ³
    -0.06
    wykle
    -0.06
    nih
    -0.06
    heten
    -0.06
    èĭį天
    -0.06
    à¯įதà¯įத
    -0.06
    ä¿ĿæĬ¤çļĦ
    -0.06
    èĮĥåĽ´å¹¿
    -0.05
    车åŃIJ
    -0.05
    ailles
    -0.05
    POSITIVE LOGITS
    קר
    0.07
    ép
    0.07
    iep
    0.07
    Inset
    0.07
    ady
    0.07
    icola
    0.07
    å¸ģ
    0.07
    iec
    0.07
    )(((
    0.07
    çľĭå¾Ĺ
    0.07
    Activations Density 0.675%

    No Known Activations