© 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. 2748
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    uhl
    -0.08
    AGR
    -0.08
    udd
    -0.07
    istros
    -0.07
    ESC
    -0.07
    olley
    -0.07
    NOP
    -0.06
    èĬľ
    -0.06
    uger
    -0.06
    è¯
    -0.06
    POSITIVE LOGITS
    èįĶ
    0.08
    åľ°æ®µ
    0.07
    èªĺ
    0.07
     ä»ĬæĹ¥
    0.07
    HTTPHeader
    0.07
    ä¹ĭæľĢ
    0.07
     fit
    0.07
     airs
    0.07
    leÅŁ
    0.07
    evers
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.