© 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. 49564
    Prev
    Next
    INDEX
    Explanations

    hand/eye/over/towards action

    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
    产åģĩ
    -0.08
    uny
    -0.07
    åıijçİ°èĩªå·±
    -0.07
     exped
    -0.06
    bourne
    -0.06
    eldorf
    -0.06
    宣读
    -0.06
    CCCC
    -0.06
    illi
    -0.06
    irati
    -0.06
    POSITIVE LOGITS
    æħ°
    0.08
    æİĴ忧
    0.07
    æĤ£
    0.07
    士å®ĺ
    0.07
    Bes
    0.07
    åĿĢ
    0.07
    æĸĩåĵ²
    0.07
    æĭħ忧
    0.07
    ä½ĵè´´
    0.07
    并èĤ©
    0.07
    Activations Density 0.048%

    No Known Activations