© 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. 55339
    Prev
    Next
    INDEX
    Explanations

    sub component

    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
    ablish
    -0.10
    lesia
    -0.09
    ноÑģÑĤÑĢан
    -0.08
    encias
    -0.08
    beau
    -0.08
    onsin
    -0.08
    Åijbb
    -0.08
    alkan
    -0.08
    ighth
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    POSITIVE LOGITS
    stract
    0.11
    tle
    0.09
    rata
    0.08
    einander
    0.08
    ordinated
    0.08
    stantial
    0.08
    scribers
    0.08
    stitute
    0.08
    .Popen
    0.08
    sequent
    0.08
    Activations Density 0.077%

    No Known Activations