© 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. 31654
    Prev
    Next
    INDEX
    Explanations

    boundaries and limits

    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
    çĤİçļĦ
    -0.08
    vind
    -0.07
    ä¿ĥ
    -0.07
    .waitFor
    -0.07
    illis
    -0.07
    æĪ³
    -0.07
    _payload
    -0.07
    SUM
    -0.07
    æĽ¦
    -0.07
    à¸ģระà¸Ĺ
    -0.07
    POSITIVE LOGITS
    çķĮ
    0.08
     faj
    0.07
    _critical
    0.07
    åıįéĿ¢
    0.07
     boundaries
    0.07
    hel
    0.07
     boundary
    0.07
    bove
    0.07
    临çķĮ
    0.07
    afe
    0.07
    Activations Density 0.005%

    No Known Activations