© 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. 3144
    Prev
    Next
    INDEX
    Explanations

    Project related code

    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
    uli
    -0.07
    elius
    -0.06
    ÑĥÑģа
    -0.06
    ran
    -0.06
    æ¨
    -0.06
    adem
    -0.06
    oghi
    -0.06
    usiai
    -0.06
    æľīæĥħ
    -0.06
     schematic
    -0.06
    POSITIVE LOGITS
    pread
    0.08
    æĽ¿å°¼
    0.08
    -pills
    0.08
    ä¹°åįķ
    0.08
    obuf
    0.07
    ixel
    0.07
    ç¥ī
    0.07
    yje
    0.07
    dney
    0.07
    å¾Ĺåħ¶
    0.07
    Activations Density 0.031%

    No Known Activations