© 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. 4073
    Prev
    Next
    INDEX
    Explanations

    coordinates and angles

    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
    Messenger
    -0.08
    erbe
    -0.07
    éļĶå¤ľ
    -0.07
    讨
    -0.07
    ambe
    -0.07
    icino
    -0.07
    _literals
    -0.07
     foc
    -0.07
    ugno
    -0.07
    ç¼Ķ
    -0.07
    POSITIVE LOGITS
    ordinal
    0.10
     ordinal
    0.09
     incremented
    0.08
     padded
    0.08
    номеÑĢ
    0.08
    extras
    0.08
     coordinates
    0.08
     interle
    0.08
    _mapper
    0.07
     номеÑĢ
    0.07
    Activations Density 0.036%

    No Known Activations