© 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. 29689
    Prev
    Next
    INDEX
    Explanations

    Mr. Hepper

    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
    -0.10
     Gain
    -0.07
    ³³³³
    -0.07
     ...\
    -0.07
     âĢ¦
    -0.06
    гÑĢ
    -0.06
    ³³³³³³³³
    -0.06
    ÑĢалÑĮ
    -0.06
    yata
    -0.06
    ³³
    -0.06
    POSITIVE LOGITS
    edly
    0.08
    ç¯ĩäºĮ
    0.08
    eson
    0.08
    uté
    0.07
    人åij½
    0.07
    æľī天
    0.07
    lern
    0.07
    cion
    0.07
    riture
    0.07
    _PAD
    0.07
    Activations Density 0.108%

    No Known Activations