© 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. 49835
    Prev
    Next
    INDEX
    Explanations

    such that

    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
    黼
    -0.07
    els
    -0.07
    es
    -0.07
    åѦæ³ķ
    -0.06
    esu
    -0.06
    da
    -0.06
    aed
    -0.06
    ae
    -0.06
    æĺİæĺ¾
    -0.06
    nd
    -0.06
    POSITIVE LOGITS
    _FL
    0.07
    tribu
    0.07
    ForKey
    0.07
    éĻIJ度çļĦ
    0.07
    (xi
    0.07
    strand
    0.07
    chetti
    0.07
    /GPL
    0.07
    æĪ²
    0.07
    -hash
    0.06
    Activations Density 0.004%

    No Known Activations