© 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. 13760
    Prev
    Next
    INDEX
    Explanations

    numbers and citations/references

    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
    åħ®
    -0.07
    ÙIJ
    -0.06
    Æ¡
    -0.06
    ç¨ĭ
    -0.06
    emek
    -0.06
    æĥ¹
    -0.06
    ède
    -0.06
    ·
    -0.06
    inge
    -0.06
    åij¨ä¸Ģ
    -0.06
    POSITIVE LOGITS
    æīĵå¼Ģæīĭæľº
    0.08
    orian
    0.08
    );}
    0.08
    ستÙĩ
    0.08
    bacher
    0.08
    <|fim_prefix|>
    0.08
    ickerView
    0.08
    ائÙĬØ©
    0.08
    ÂŃt
    0.07
    让åŃ©åŃIJ们
    0.07
    Activations Density 0.218%

    No Known Activations