© 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. 10413
    Prev
    Next
    INDEX
    Explanations

    probably

    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
     ÑıкобÑĭ
    -0.11
    <|box_end|>
    -0.11
     supposedly
    -0.10
    presso
    -0.10
    å±ħçĦ¶æĺ¯
    -0.10
    ç«ŁçĦ¶
    -0.10
    buster
    -0.09
     allegedly
    -0.09
    å±ħçĦ¶
    -0.09
     seemingly
    -0.09
    POSITIVE LOGITS
    ÑģÑĮ
    0.08
    erweise
    0.07
     saja
    0.07
    mente
    0.07
    ä¸įä¼ļæľī
    0.07
     won
    0.06
     sooner
    0.06
     not
    0.06
    ly
    0.06
    Ķ
    0.06
    Activations Density 0.033%

    No Known Activations