© 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. 4357
    Prev
    Next
    INDEX
    Explanations

    eigenvalues and vectors

    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
    Âł
    -0.07
    rig
    -0.07
    elm
    -0.07
    åĴĮ交æµģ
    -0.07
    鬣
    -0.07
     Mig
    -0.07
    cac
    -0.07
    ash
    -0.06
    éļĪ
    -0.06
     pare
    -0.06
    POSITIVE LOGITS
    yks
    0.08
    ëĭ¨
    0.08
    leck
    0.08
    ר×ķף
    0.07
    atts
    0.07
    æĽĨ
    0.07
    帳
    0.07
    æľĥéķ·
    0.07
    å¸IJ
    0.07
    ais
    0.07
    Activations Density 0.028%

    No Known Activations