© 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. 19928
    Prev
    Next
    INDEX
    Explanations

    document begin or add

    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
     âĢ¦
    -0.09
    _FILENAME
    -0.07
    æ¯ķç«Ł
    -0.06
    èĤĩ
    -0.06
    \_
    -0.06
    âĢ¦
    -0.06
    áĥIJáĥĵ
    -0.06
    轻轻ä¸Ģ
    -0.06
    ž
    -0.06
     SINH
    -0.06
    POSITIVE LOGITS
    <|fim_middle|>
    0.08
     asses
    0.08
    yed
    0.07
     fucking
    0.07
     inves
    0.07
    coding
    0.07
    ãģijãĤĵ
    0.07
     fucked
    0.07
    åłĤ
    0.07
     chall
    0.07
    Activations Density 0.734%

    No Known Activations