© 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. 49768
    Prev
    Next
    INDEX
    Explanations

    March dates and times

    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
    enor
    -0.07
    á»ijt
    -0.07
    лайн
    -0.07
    BER
    -0.07
    IFY
    -0.07
    欺
    -0.06
    /null
    -0.06
    _INCLUDED
    -0.06
    oS
    -0.06
    è°ħ
    -0.06
    POSITIVE LOGITS
    WSC
    0.09
    illy
    0.08
    åıĪæĿ¥
    0.07
    icie
    0.07
    pasar
    0.07
    عÙĪ
    0.07
    éĢ
    0.07
    avig
    0.07
    æĤł
    0.07
    æĪij们åıĪ
    0.06
    Activations Density 0.027%

    No Known Activations