© 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. 57999
    Prev
    Next
    INDEX
    Explanations

    non-empty or zero

    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
    oble
    -0.07
    å·¥æķ´
    -0.07
    eration
    -0.07
     toeg
    -0.07
    eran
    -0.07
    éĤĢ
    -0.07
    ç®ĹäºĨ
    -0.07
    alette
    -0.07
    天æĪIJ
    -0.07
    erne
    -0.07
    POSITIVE LOGITS
    empty
    0.08
    duk
    0.08
    æľī人
    0.07
    EMPTY
    0.07
     empty
    0.07
     Empty
    0.07
    为空
    0.07
    eden
    0.07
    涣
    0.07
    NotEmpty
    0.07
    Activations Density 0.011%

    No Known Activations