© 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. 26904
    Prev
    Next
    INDEX
    Explanations

    constants and coefficients

    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
    TECTED
    -0.08
    tock
    -0.08
    resentation
    -0.07
    магни
    -0.07
    anut
    -0.07
    ulihan
    -0.07
     éner
    -0.07
    ä¸īé¤IJ
    -0.07
    odr
    -0.07
    æŶæį·
    -0.07
    POSITIVE LOGITS
     governing
    0.07
    Values
    0.07
    æ·«
    0.07
     values
    0.07
    å²ļ
    0.07
    oper
    0.07
    werte
    0.06
    unst
    0.06
    严å®Ī
    0.06
    pel
    0.06
    Activations Density 0.002%

    No Known Activations