© 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. 57386
    Prev
    Next
    INDEX
    Explanations

    links or URLs

    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
    æĪijçļĦç¥Ŀç¦ı
    -0.10
    ContentLoaded
    -0.10
    ableObject
    -0.09
    _LOADED
    -0.08
    ÑģÑĤÑĢой
    -0.08
    大åıĺ
    -0.08
    vio
    -0.08
    inflam
    -0.08
    ilog
    -0.08
    umos
    -0.08
    POSITIVE LOGITS
     https
    0.07
    leven
    0.07
    @
    0.07
    [@
    0.06
     @
    0.06
    å®ŀéĻħéĹ®é¢ĺ
    0.06
    æıIJéĹ®èĢħ
    0.06
    ong
    0.06
    æŃ£ç¡®çļĦæĺ¯
    0.06
    gor
    0.06
    Activations Density 0.118%

    No Known Activations