© 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. 2567
    Prev
    Next
    INDEX
    Explanations

    application and its uses

    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
    waard
    -0.09
     muka
    -0.09
    itage
    -0.08
    waan
    -0.08
    à¹Ĩ
    -0.08
    /null
    -0.08
     ÑĥпÑĢа
    -0.08
    ftime
    -0.08
    resh
    -0.08
    endom
    -0.08
    POSITIVE LOGITS
    sv
    0.08
    lications
    0.08
    sw
    0.08
    ss
    0.08
    -ready
    0.07
    /octet
    0.07
    /vnd
    0.07
    sworth
    0.07
    à¸ŀลิà¹Ģà¸Ħ
    0.07
    à¸ŀลิà¹Ģà¸Ħà¸Ĭัà¸Ļ
    0.06
    Activations Density 0.151%

    No Known Activations