© 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. 46107
    Prev
    Next
    INDEX
    Explanations

    stainless steel

    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
    çªį
    -0.08
    gons
    -0.08
    .contents
    -0.08
     cadr
    -0.07
     amplitude
    -0.07
    igon
    -0.07
    .Gravity
    -0.07
    ually
    -0.07
    ×ķ×ķת
    -0.07
    /angular
    -0.07
    POSITIVE LOGITS
     stainless
    0.10
    ä¸įéĶĪéĴ¢
    0.08
     Stainless
    0.08
    _perf
    0.07
    ropol
    0.07
    amet
    0.07
     Edelstahl
    0.07
    idable
    0.07
    éĴĽ
    0.06
     неÑĢжавеÑİÑīей
    0.06
    Activations Density 0.015%

    No Known Activations