© 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. 55964
    Prev
    Next
    INDEX
    Explanations

    mathematical groups and algebra

    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
    undial
    -0.08
    менÑĥ
    -0.08
    åı«åģļ
    -0.08
    çļĦéĥ½æĺ¯
    -0.08
    enzio
    -0.08
    ä½ľçĤº
    -0.07
    è¿Ļæī¹
    -0.07
    .poll
    -0.07
    ä¸ĩåıĺ
    -0.07
    ]->
    -0.07
    POSITIVE LOGITS
     whose
    0.09
    ä¸įåIJĮäºİ
    0.07
    ä¸Ķåľ¨
    0.07
    ä¸Ķ
    0.06
     representing
    0.06
    whose
    0.06
    åIJĮ
    0.06
     satisfying
    0.06
    çĶĺéľ²
    0.06
     majeure
    0.06
    Activations Density 0.031%

    No Known Activations