© 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. 25867
    Prev
    Next
    INDEX
    Explanations

    hexadecimal or base64 encoding

    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
    ús
    -0.07
    usak
    -0.07
    xd
    -0.07
    ively
    -0.07
    ally
    -0.06
    ä¸ĩä¸Ģ
    -0.06
    uret
    -0.06
    ebb
    -0.06
    wab
    -0.06
    æīĭæĭ¿
    -0.06
    POSITIVE LOGITS
     Mel
    0.08
    æģ©æĸ¯
    0.08
    Õ£
    0.07
    Ùģات
    0.07
    ãģįãģ¯
    0.07
    Ĩµ
    0.07
    pcodes
    0.07
    ãĥĨãĥ¼ãĤ·ãĥ§ãĥ³
    0.07
    ignment
    0.06
    GRAM
    0.06
    Activations Density 0.032%

    No Known Activations