© 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. 61118
    Prev
    Next
    INDEX
    Explanations

    shape descriptors

    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
    -0.07
    _ERRORS
    -0.06
     deal
    -0.06
    åģ¥åħ¨
    -0.06
    emor
    -0.06
    èĩªæľī
    -0.06
    Errors
    -0.06
     decimal
    -0.06
    ç»Ĭ
    -0.06
     lever
    -0.06
    POSITIVE LOGITS
    ribbon
    0.09
    riad
    0.09
    <|box_end|>
    0.08
    Disconnected
    0.08
    .ends
    0.08
    yeong
    0.08
    çĨŁäºĨ
    0.08
    ä¼ģä¸ļèį£èªī
    0.08
    çī¹éķ¿
    0.08
    è¿ŀéĢļ
    0.08
    Activations Density 0.004%

    No Known Activations