© 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. 45125
    Prev
    Next
    INDEX
    Explanations

    in part

    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
    æľīèī²
    -0.07
    thur
    -0.06
    IMA
    -0.06
    oom
    -0.06
    vla
    -0.06
    IM
    -0.06
     outstanding
    -0.06
     Ken
    -0.06
    -"
    -0.06
     whose
    -0.06
    POSITIVE LOGITS
    _timezone
    0.09
    alse
    0.08
    ivirus
    0.08
    SSERT
    0.08
    inj
    0.08
    ambo
    0.07
    ÃŃfico
    0.07
    ighton
    0.07
    alties
    0.07
    sdale
    0.07
    Activations Density 0.002%

    No Known Activations