© 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. 24508
    Prev
    Next
    INDEX
    Explanations

    `n` or `k` followed by `=`

    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
    ohlen
    -0.07
    å°±ä¸Ģ缴
    -0.07
    assel
    -0.07
    erville
    -0.06
    kurat
    -0.06
    onio
    -0.06
    commit
    -0.06
    Call
    -0.06
    注æĦı
    -0.06
    oit
    -0.06
    POSITIVE LOGITS
    quis
    0.07
     {}".
    0.07
    ẩm
    0.07
    urin
    0.07
    ù
    0.07
    dre
    0.07
    úr
    0.07
    ữ
    0.07
    uern
    0.07
     bÃłn
    0.07
    Activations Density 0.010%

    No Known Activations