© 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. 44000
    Prev
    Next
    INDEX
    Explanations

    halogen, diode, transfer

    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
    ldr
    -0.07
    çĻ¾ç§ijåħ¨ä¹¦
    -0.07
    .xxx
    -0.07
    使çĶ¨èµ·æĿ¥
    -0.06
    ä½Ĩæĺ¯è¿Ļ个
    -0.06
    家ä¼Ļ
    -0.06
    itarra
    -0.06
    ADVERTISEMENT
    -0.06
    ä¸įå¤ļçļĦ
    -0.06
    åij¨æŁIJ
    -0.06
    POSITIVE LOGITS
    reserve
    0.07
    leb
    0.07
    é»ŀå¿ĥ
    0.07
    _elt
    0.07
    dap
    0.07
    asiun
    0.06
    :on
    0.06
    ר×ļ
    0.06
    timeofday
    0.06
    antd
    0.06
    Activations Density 0.574%

    No Known Activations