© 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. 2815
    Prev
    Next
    INDEX
    Explanations

    many number

    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
    åħħ
    -0.07
    .ToolTip
    -0.07
     deu
    -0.07
    _DEV
    -0.07
    æŃ£æľ¬
    -0.07
    iks
    -0.07
    azer
    -0.07
    antz
    -0.07
    çŁ³æĻ¯
    -0.07
    ou
    -0.07
    POSITIVE LOGITS
    寡
    0.07
    alon
    0.07
    èĥ½ä»İ
    0.07
    éĤ£æł·çļĦ
    0.07
    éĤ£æ®µ
    0.06
    малÑĮ
    0.06
    åľ¨éĤ£éĩĮ
    0.06
     capable
    0.06
    éĤ£èĪ¬
    0.06
    临
    0.06
    Activations Density 0.189%

    No Known Activations