© 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. 21310
    Prev
    Next
    INDEX
    Explanations

    call it

    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
    opard
    -0.07
    åıªåī©ä¸ĭ
    -0.07
    æ·
    -0.07
    ä¸ĢæİĴ
    -0.07
    ards
    -0.06
    venil
    -0.06
    ornings
    -0.06
    abd
    -0.06
    OGRAPH
    -0.06
    æĵįä½ľä¸Ń
    -0.06
    POSITIVE LOGITS
     ''.
    0.10
     "".
    0.10
    æĪijåIJ§
    0.09
     ','.
    0.07
    å¾ħå®ļ
    0.07
    ('').
    0.07
    *".
    0.07
    ively
    0.07
    kund
    0.07
    иÑģло
    0.07
    Activations Density 0.061%

    No Known Activations