© 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. 45859
    Prev
    Next
    INDEX
    Explanations

    Respondents

    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
    es
    -0.10
    Âł
    -0.09
    is
    -0.07
    al
    -0.07
    ai
    -0.07
    çļĦ
    -0.07
    m
    -0.07
    u
    -0.07
    d
    -0.06
    an
    -0.06
    POSITIVE LOGITS
    utki
    0.09
    羣å®ŀæĢ§è´Łè´£
    0.08
    egov
    0.08
    jenigen
    0.08
    uncul
    0.08
    à¹Īาà¸Ļัà¹īà¸Ļ
    0.08
     undermin
    0.07
    人åħ¬
    0.07
    鼶鼶
    0.07
    /MPL
    0.07
    Activations Density 0.005%

    No Known Activations