© 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. 10003
    Prev
    Next
    INDEX
    Explanations

    disemb

    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
    ohl
    -0.08
    esome
    -0.08
     Phong
    -0.08
    nitz
    -0.07
    Ø´Ùģ
    -0.07
    conds
    -0.07
    баÑĢ
    -0.07
    _micro
    -0.07
    å®ŀå¤Ħ
    -0.07
    SYM
    -0.07
    POSITIVE LOGITS
     Discipl
    0.07
    è¶ħåĩº
    0.06
     disemb
    0.06
    åIJĮ
    0.06
    .mask
    0.06
     Gover
    0.06
     mary
    0.06
    ÉĻrÉĻ
    0.06
    èĵī
    0.06
    scriptions
    0.06
    Activations Density 0.163%

    No Known Activations