© 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. 13649
    Prev
    Next
    INDEX
    Explanations

    percentage increase or decrease

    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
    åįĬä»·
    -0.07
    ä¸Ģ个ç®ĢåįķçļĦ
    -0.07
    å°º
    -0.07
    _SEPARATOR
    -0.07
    ä¸Ĭå¸Ŀ
    -0.06
    ä¸īåĪĨ
    -0.06
    ordial
    -0.06
    Ñĥда
    -0.06
    Resolved
    -0.06
    ä¸ĭåįĬ
    -0.06
    POSITIVE LOGITS
     previous
    0.09
    previous
    0.08
     vorig
    0.07
    semb
    0.07
     Rekord
    0.07
    _previous
    0.07
    ervisor
    0.07
    phy
    0.07
    _filepath
    0.07
    ffer
    0.07
    Activations Density 0.162%

    No Known Activations