© 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. 45215
    Prev
    Next
    INDEX
    Explanations

    corner

    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
    ectes
    -0.07
    å¡ĺéķĩ
    -0.07
    appa
    -0.07
    adena
    -0.06
    è®¤è®¤çľŁ
    -0.06
    tober
    -0.06
    $ret
    -0.06
    ãģ¨è¨ĢãģĪãģ°
    -0.06
    roke
    -0.06
    æĸ°æĿIJæĸĻæľīéĻIJåħ¬åı¸
    -0.06
    POSITIVE LOGITS
    ä¹ĭ称çļĦ
    0.09
    wane
    0.08
    issé
    0.07
    ’T
    0.07
    âĦ¢
    0.07
    elado
    0.07
    azgo
    0.07
    ä¸ĩå²ģ
    0.07
    ´t
    0.07
    ener
    0.07
    Activations Density 0.764%

    No Known Activations