© 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. 65216
    Prev
    Next
    INDEX
    Explanations

    line segments, parallel, students

    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
    jut
    -0.07
    elius
    -0.07
    Thunk
    -0.07
    æĶ¯æµģ
    -0.07
    åŃĺåħ¥
    -0.07
     Fisc
    -0.07
    ?id
    -0.07
     cad
    -0.07
    è·Įèĩ³
    -0.07
    recht
    -0.07
    POSITIVE LOGITS
    å¹³è¡Į
    0.10
    parallel
    0.09
     parallel
    0.09
     Parallel
    0.08
    upil
    0.08
    Parallel
    0.08
    anny
    0.07
    dy
    0.07
     afast
    0.07
    é«ĺæĺĤ
    0.07
    Activations Density 0.001%

    No Known Activations