© 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. 56039
    Prev
    Next
    INDEX
    Explanations

    more than

    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
    åIJĮæł·
    -0.09
    æł¼å¤ĸ
    -0.08
     likewise
    -0.08
    rans
    -0.07
    ometr
    -0.07
    ijIJ
    -0.07
    以åıĬåħ¶ä»ĸ
    -0.07
    ugeot
    -0.07
    quiv
    -0.07
    åħĭæĸ¯åĿ¦
    -0.07
    POSITIVE LOGITS
     than
    0.14
    _than
    0.12
    than
    0.11
     Than
    0.11
     niż
    0.10
    Than
    0.10
     inkább
    0.09
     THAN
    0.09
     daripada
    0.09
     rather
    0.09
    Activations Density 0.070%

    No Known Activations