© 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. 50392
    Prev
    Next
    INDEX
    Explanations

    reverse direction, reversed colors, reverse engineer, reverse side

    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
    å®ŀå¤Ħ
    -0.08
    ziger
    -0.08
    ìĭ¶
    -0.08
    ÃŃž
    -0.08
    zelfde
    -0.07
    lients
    -0.07
    erator
    -0.07
    erval
    -0.07
    麾ä¸ĭ
    -0.07
     Pesso
    -0.07
    POSITIVE LOGITS
    pective
    0.10
    ive
    0.09
    (er
    0.09
    es
    0.08
    iculum
    0.08
    pectives
    0.08
    ÑģмоÑĤÑĢÑı
    0.08
    orld
    0.07
    ible
    0.07
    ely
    0.07
    Activations Density 0.013%

    No Known Activations