© 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. 26735
    Prev
    Next
    INDEX
    Explanations

    free, open, ring R

    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
    által
    -0.08
    ìĿĺ를
    -0.08
    usk
    -0.07
    è°ħ
    -0.07
    liwoÅĽÄĩ
    -0.07
    gab
    -0.07
    ç½ķ
    -0.07
    ä¾Ŀæŧæĺ¯
    -0.07
    æĿ¥ä¹ĭ
    -0.07
     bowiem
    -0.07
    POSITIVE LOGITS
    æ¾Ħ
    0.07
    山人
    0.07
    estic
    0.07
    ä¸Ķ
    0.07
     appunto
    0.07
    otent
    0.07
    æĺĩ
    0.06
    .land
    0.06
    æĸ°æĿIJ
    0.06
    è¶ħ
    0.06
    Activations Density 0.010%

    No Known Activations