© 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. 31815
    Prev
    Next
    INDEX
    Explanations

    surface topology momentum wave-vector

    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
    elage
    -0.07
    seb
    -0.07
    åħ¨çľģ
    -0.07
    สา
    -0.06
    orsa
    -0.06
    isis
    -0.06
    osan
    -0.06
    undra
    -0.06
    涵
    -0.06
     kai
    -0.06
    POSITIVE LOGITS
    ç®Ģç«ł
    0.09
    çĭ©
    0.08
    wijk
    0.08
    èģĨ
    0.08
     tess
    0.08
    opal
    0.08
    å±ķéĶĢ
    0.08
    æ¯Ķä»·
    0.07
    çŁ¢
    0.07
     crist
    0.07
    Activations Density 0.004%

    No Known Activations