© 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. 47992
    Prev
    Next
    INDEX
    Explanations

    assignment of values

    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
    MMC
    -0.07
    utam
    -0.06
    amar
    -0.06
    inge
    -0.06
     dogod
    -0.06
    holt
    -0.06
    iris
    -0.06
    apore
    -0.06
     ({
    -0.06
    utan
    -0.06
    POSITIVE LOGITS
    æľĢä½³çŃĶæ¡Ī
    0.07
    第ä¸ĢæŶéĹ´
    0.07
     Fili
    0.07
    éĩĬ
    0.06
    enner
    0.06
    ESTE
    0.06
    éĩĪ
    0.06
    வà¯ģà®®à¯į
    0.06
     Parten
    0.06
    _perms
    0.06
    Activations Density 0.162%

    No Known Activations