© 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. 904
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    loquent
    -0.09
    ëħĢ
    -0.07
    arget
    -0.07
     overrun
    -0.07
    å½¢çļĦ
    -0.07
    atisf
    -0.07
    ç»´
    -0.07
     exhaus
    -0.07
    ä¸ĭ表
    -0.06
     peri
    -0.06
    POSITIVE LOGITS
     itself
    0.08
    åıĬåħ¶
    0.08
    udir
    0.07
     Moff
    0.07
    OST
    0.07
     indirectly
    0.07
     Banks
    0.07
    ÑĨеÑĢ
    0.07
    eer
    0.07
    åı«æĪij
    0.07
    Activations Density 0.007%

    No Known Activations