© 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. 34388
    Prev
    Next
    INDEX
    Explanations

    git commands and programming interfaces

    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
    ÅĤow
    -0.07
    èĦijè¢ĭ
    -0.07
    roat
    -0.07
    çķ
    -0.07
    å¼ĢçªĹ
    -0.07
    .walk
    -0.06
    uable
    -0.06
    äºĶå®ĺ
    -0.06
    /native
    -0.06
    ued
    -0.06
    POSITIVE LOGITS
    _CONTINUE
    0.08
    æµ·æ¶Ľ
    0.07
    åŁºç¡Ģ设æĸ½
    0.07
    rien
    0.06
    åŁºç¡Ģ设æĸ½å»ºè®¾
    0.06
    强åĪ¶æݪæĸ½
    0.06
     пÑĥÑĤ
    0.06
    ÙĪت
    0.06
     doubts
    0.06
    åīįæĸ¹
    0.06
    Activations Density 0.404%

    No Known Activations