© 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. 57456
    Prev
    Next
    INDEX
    Explanations

    variable assignments or declarations

    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
    :true
    -0.08
    PLEX
    -0.08
    _=
    -0.07
     '_'
    -0.07
    &&!
    -0.07
    :false
    -0.07
    ]>=
    -0.07
    )->
    -0.07
    >_
    -0.07
    ä¸įåı¯æĢķ
    -0.07
    POSITIVE LOGITS
    atin
    0.07
    leh
    0.07
    leck
    0.06
    åIJ«éĩij
    0.06
    ogen
    0.06
    ãģıãĤĬ
    0.06
    auen
    0.06
    avam
    0.06
    istos
    0.06
    elin
    0.06
    Activations Density 0.197%

    No Known Activations