© 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. 50468
    Prev
    Next
    INDEX
    Explanations

    area of, spread

    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
    arch
    -0.07
    iksaan
    -0.07
    à¹Ĥà¸Ħรà¸ĩ
    -0.07
    INGER
    -0.06
    ÑħваÑĤÑĭ
    -0.06
    èģĭ
    -0.06
    æĤ´
    -0.06
    -dismiss
    -0.06
    __/
    -0.06
    erk
    -0.06
    POSITIVE LOGITS
    å¹³åĿĩåĪĨ
    0.08
     spread
    0.08
    /editor
    0.08
    spread
    0.08
    cw
    0.07
    åįĩ
    0.07
     Spread
    0.07
    åĪĨæŶ
    0.07
     spreading
    0.07
    Spread
    0.07
    Activations Density 0.056%

    No Known Activations