© 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. 41611
    Prev
    Next
    INDEX
    Explanations

    representative of

    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
    agne
    -0.08
    æľīäºĽåľ°æĸ¹
    -0.07
    ardo
    -0.07
    è·¨åĮºåŁŁ
    -0.07
    AGES
    -0.06
    alis
    -0.06
    meta
    -0.06
    éĤ£äºĽäºº
    -0.06
    cke
    -0.06
    .Debugger
    -0.06
    POSITIVE LOGITS
     representative
    0.08
    หà¸Ļึà¹Īà¸ĩà¸Ĥà¸Ńà¸ĩ
    0.08
     cualquiera
    0.08
    memberof
    0.07
    okka
    0.07
    eson
    0.07
    /all
    0.07
    ÑģÑĤÑĮ
    0.07
    ä»£è¡¨ä½ľ
    0.07
    åıĸå¾ĹèģĶç³»
    0.06
    Activations Density 0.357%

    No Known Activations