© 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. 1606
    Prev
    Next
    INDEX
    Explanations

    lists followed by 'and'

    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
    ãĢģ
    -0.08
    åİ¥
    -0.08
    )ãĢģ
    -0.08
    åıĪå¦Ĥ
    -0.08
     Ñģобой
    -0.07
    unte
    -0.07
    ãģĿãģĨãģ§
    -0.07
    ãĢįãĢģãĢĮ
    -0.07
    ãĢģãĢģ
    -0.07
    éĶĻ误æĪĸ
    -0.07
    POSITIVE LOGITS
    etc
    0.09
    etz
    0.08
    ä¸įèµ·
    0.07
     ultimately
    0.07
    borg
    0.07
    æľīéĻIJ
    0.07
    满
    0.07
    ä¸įå¼Ģ
    0.07
    év
    0.07
    çŃī缸åħ³
    0.07
    Activations Density 0.264%

    No Known Activations