© 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. 50437
    Prev
    Next
    INDEX
    Explanations

    representation theory

    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
    ago
    -0.07
    пÑıÑĤ
    -0.07
    æı½
    -0.07
    åį«å£«
    -0.07
    æ¡£
    -0.07
    å°ıå§IJ
    -0.07
    ampa
    -0.07
    gge
    -0.06
    èħ»
    -0.06
    æĭ©æł¡
    -0.06
    POSITIVE LOGITS
    erez
    0.08
    Hooks
    0.07
    Lens
    0.07
    szak
    0.07
     Tears
    0.07
    eye
    0.07
    .getColor
    0.07
    uru
    0.07
    encial
    0.06
    ucha
    0.06
    Activations Density 0.003%

    No Known Activations