© 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. 51584
    Prev
    Next
    INDEX
    Explanations

    json object keys or variable names

    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
    æ¯Ľæ¯Ľ
    -0.08
    çijķ
    -0.07
    rror
    -0.07
     gratu
    -0.07
    äºİå¿ĥ
    -0.07
    воÑĢо
    -0.07
    èĩ³ä»Ĭå·²
    -0.07
     manca
    -0.07
    fully
    -0.07
    inspace
    -0.07
    POSITIVE LOGITS
    åij¦
    0.09
    è¥Ħ
    0.07
    emet
    0.07
    éĶĢåĶ®éĥ¨
    0.06
    #{
    0.06
    æ°ı
    0.06
    ä¸įæĻĤ
    0.06
     bulundu
    0.06
    avigation
    0.06
    .unwrap
    0.06
    Activations Density 0.002%

    No Known Activations