© 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. 7857
    Prev
    Next
    INDEX
    Explanations

    shape / shaped / shapes / shaping

    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
    aries
    -0.10
    ary
    -0.09
    ë¦Ħ
    -0.09
    ä¸įåĨ³
    -0.08
    ìĤ¬íķŃ
    -0.08
    opher
    -0.08
    naire
    -0.08
    chie
    -0.08
    ship
    -0.08
    Úº
    -0.08
    POSITIVE LOGITS
    indsight
    0.10
     mẽ
    0.08
    lessly
    0.08
    neider
    0.08
    orthand
    0.08
    lets
    0.08
    lessness
    0.08
    atters
    0.08
    fully
    0.08
    ometown
    0.07
    Activations Density 0.023%

    No Known Activations