© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64020
    Prev
    Next
    INDEX
    Explanations

    right shift, division, and sizeof operators

    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
    ammt
    -0.08
    antau
    -0.08
    korb
    -0.07
    iedad
    -0.07
    edido
    -0.07
    peak
    -0.07
    yder
    -0.07
    attan
    -0.07
    ÙĦائ
    -0.07
    iano
    -0.07
    POSITIVE LOGITS
    gnore
    0.07
    طاÙĨ
    0.07
    çIJ³å¨ľ
    0.06
    lse
    0.06
    æĻ®æĭī
    0.06
    æĪĺçķ¥æĢ§
    0.06
    æĨ¬
    0.06
    ä¹ĭ以
    0.06
    æľīè¿ĩ
    0.06
    /slick
    0.06
    Activations Density 0.002%

    No Known Activations