© 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. 26392
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    éĿłå·¦
    -0.07
    oppel
    -0.07
    =url
    -0.07
    åħīéĺ´
    -0.07
    ihan
    -0.06
    Ĥ¬
    -0.06
    Located
    -0.06
    å¼Ģåı£è¯´éģĵ
    -0.06
    æg
    -0.06
    atable
    -0.06
    POSITIVE LOGITS
    sla
    0.07
    ìłĢ
    0.07
    _stub
    0.07
    oris
    0.07
    禹
    0.07
    _BACKEND
    0.07
    θεν
    0.07
    inja
    0.07
    alat
    0.07
    erea
    0.07
    Activations Density 0.004%

    No Known Activations