© 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. 25434
    Prev
    Next
    INDEX
    Explanations

    connecting components or parts

    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
    çŀ»
    -0.07
    âĢ¦]
    -0.07
    orate
    -0.07
    gev
    -0.07
    ivr
    -0.07
    otella
    -0.07
    åľ¨çĽ®åīį
    -0.07
    ivio
    -0.07
    icken
    -0.07
    è¡Įä¹ĭ
    -0.06
    POSITIVE LOGITS
    annel
    0.07
    åıĬåħ¶
    0.07
    oba
    0.07
    缸è¾ħ缸æĪIJ
    0.07
     jaoks
    0.06
    åĴĮ
    0.06
     ìĿĺíķ´
    0.06
    rlen
    0.06
    俱ä¹IJéĥ¨
    0.06
    æĪĸåħ¶
    0.06
    Activations Density 0.013%

    No Known Activations