© 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. 63330
    Prev
    Next
    INDEX
    Explanations

    sphere, circle, distance, latitude, sky

    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
    å¢ĥ
    -0.08
    ersi
    -0.08
    èĹķ
    -0.07
    teca
    -0.07
     hormon
    -0.07
    æİĴåľ¨
    -0.07
    顺åı£
    -0.07
    éħįåIJĪ
    -0.07
     horm
    -0.06
    èĽ
    -0.06
    POSITIVE LOGITS
     spherical
    0.09
    é¼ĵèµ·
    0.08
    ç»ı纬
    0.08
     arcs
    0.08
     latitude
    0.08
    åľ°åĽ¾
    0.08
    stial
    0.08
    赤éģĵ
    0.08
    rix
    0.08
    Latitude
    0.08
    Activations Density 0.008%

    No Known Activations