© 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. 33787
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    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
    assin
    -0.08
    åªĽ
    -0.07
    iolet
    -0.07
    oola
    -0.07
    å¤ĩæ¡Īåı·
    -0.07
    èįĺ
    -0.07
     anonyme
    -0.07
    rieve
    -0.07
    енÑģа
    -0.06
    æ·ij女
    -0.06
    POSITIVE LOGITS
     ((*
    0.10
    edis
    0.08
    åijĢ
    0.07
     ‘
    0.07
    ombo
    0.07
    åħ¹
    0.06
    æī©åħħ
    0.06
     ’
    0.06
    orama
    0.06
    _crc
    0.06
    Activations Density 0.015%

    No Known Activations