© 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. 40676
    Prev
    Next
    INDEX
    Explanations

    list in procedures

    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¯¹ä½łçļĦ
    -0.07
     (
    -0.06
    ä¿¡
    -0.06
    åħ·æľī以ä¸ĭ
    -0.06
    -0.06
     w
    -0.06
     H
    -0.06
     -
    -0.06
    åħĭéĩĮ
    -0.06
     Pur
    -0.06
    POSITIVE LOGITS
     theirs
    0.08
     ours
    0.08
    缸符
    0.08
     اÙĦØŃرÙĬرÙĬ
    0.08
    è¨Ń
    0.08
    ENAME
    0.08
     Salvini
    0.08
     à¤īनà¥įह
    0.08
    PTION
    0.08
    _buffer
    0.08
    Activations Density 0.009%

    No Known Activations