© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48295
    Prev
    Next
    INDEX
    Explanations

    licensing agreements

    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
    Ø©
    -0.09
    gether
    -0.08
    áĥ£áĥłáĥĺ
    -0.07
    ous
    -0.07
     vụ
    -0.07
    ếu
    -0.07
    ultipart
    -0.07
    lement
    -0.07
    relude
    -0.07
    ughter
    -0.07
    POSITIVE LOGITS
    го
    0.07
    iern
    0.07
    Ľ
    0.07
    opus
    0.07
    .VAL
    0.07
    imson
    0.07
    oine
    0.07
    ยà¸ģ
    0.07
    oord
    0.07
    achus
    0.07
    Activations Density 0.020%

    No Known Activations