© 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. 43339
    Prev
    Next
    INDEX
    Explanations

    prince among men

    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
    gnore
    -0.09
    ulle
    -0.08
    å¿ĥæľī
    -0.08
    Tweet
    -0.08
    umul
    -0.08
    hey
    -0.08
    æ¬łç¨İ
    -0.08
    presenta
    -0.07
    /tool
    -0.07
    Colle
    -0.07
    POSITIVE LOGITS
    isle
    0.06
     fucking
    0.06
    滨河
    0.06
    hb
    0.06
    mán
    0.06
    âĢ¦âĢ¦
    0.06
    寮
    0.06
    icode
    0.06
    éĩijä¸Ŀ
    0.06
    è·Łè¸ª
    0.06
    Activations Density 0.433%

    No Known Activations