© 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. 24377
    Prev
    Next
    INDEX
    Explanations

    subscript indices _i, _t, _n

    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
    Ĺ
    -0.07
    å¹½
    -0.06
    åı·
    -0.06
    uns
    -0.06
    æĽĻ
    -0.06
    DataMember
    -0.06
    казÑĭ
    -0.06
    δη
    -0.06
    ำ
    -0.06
    uo
    -0.06
    POSITIVE LOGITS
    loser
    0.08
    entine
    0.08
    éĺ¿å§Ĩæĸ¯
    0.07
    CanBe
    0.07
    ä¸ĢçĽ´ä»¥
    0.07
    eldes
    0.07
    ieras
    0.07
    วรร
    0.07
    ase
    0.07
    UCH
    0.07
    Activations Density 0.015%

    No Known Activations