© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14093
    Prev
    Next
    INDEX
    Explanations

    dome ellipsoids surfaces

    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
    agnol
    -0.08
    çģ«è½¦ç¥¨
    -0.08
    _lane
    -0.08
     ÑĢазвод
    -0.08
    游åĽŃ
    -0.07
    ATIC
    -0.07
    ãĤ¬ãĥ©
    -0.07
    å¾Ĵå¼Ł
    -0.07
    utters
    -0.07
    æĸ°æľĪ
    -0.07
    POSITIVE LOGITS
    åĽĽéĿ¢
    0.09
    ä¸īéĿ¢
    0.08
     projecting
    0.07
     cylindrical
    0.07
     spheres
    0.07
     dome
    0.07
     spherical
    0.07
     xyz
    0.07
    ä»°
    0.07
    xyz
    0.07
    Activations Density 0.020%

    No Known Activations