© 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. 63649
    Prev
    Next
    INDEX
    Explanations

    company, enrichment, require, test, above, waste

    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
    manos
    -0.08
    ippy
    -0.08
    esel
    -0.08
    宽æĿ¾
    -0.08
    olet
    -0.07
    tees
    -0.07
    svar
    -0.07
    PROPERTY
    -0.07
    ä¸įæĹ©
    -0.07
    ants
    -0.07
    POSITIVE LOGITS
    Âł
    0.08
    æŃ¤é¡¹
    0.07
    æѤ
    0.06
    asa
    0.06
    èĩªè¾¾
    0.06
    ä¸ĬåĽ¾
    0.06
    å¦Ĥæŀľè¦ģ
    0.06
    ¥
    0.06
    èĭ¥åľ¨
    0.06
    漫天
    0.06
    Activations Density 0.001%

    No Known Activations