© 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. 13190
    Prev
    Next
    INDEX
    Explanations

    side, face, surface

    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
    ä¸įæĹ©
    -0.07
    obox
    -0.07
    æĬĬæĪijçļĦ
    -0.07
    æĬĬäºĭæĥħ
    -0.07
    -inf
    -0.06
    .fit
    -0.06
     Hear
    -0.06
    yed
    -0.06
    åĵ½åĴ½
    -0.06
    cir
    -0.06
    POSITIVE LOGITS
     surfaces
    0.13
    -facing
    0.12
    åıįéĿ¢
    0.12
    æľĿåIJij
    0.12
    ä¸ĢéĿ¢
    0.12
    çļĦä¸ĢéĿ¢
    0.11
     facing
    0.11
     faces
    0.11
    æŃ£éĿ¢
    0.11
    èĥĮéĿ¢
    0.11
    Activations Density 0.158%

    No Known Activations