© 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. 46957
    Prev
    Next
    INDEX
    Explanations

    supposed to, meant to, write to

    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
    anker
    -0.07
    itera
    -0.06
     ÑģмÑĭÑģла
    -0.06
    {id
    -0.06
    ãģ¥
    -0.06
    æŶéľĢè¦ģ
    -0.06
     Ø«
    -0.06
    ثر
    -0.06
    poses
    -0.06
    Lost
    -0.06
    POSITIVE LOGITS
     somehow
    0.08
    à¹Ģà¸Ļ
    0.08
    kje
    0.08
    auc
    0.08
    iddy
    0.07
    ä¸Ģç³»åĪĹçļĦ
    0.07
    忽çķ¥
    0.07
    rown
    0.07
    зÑĢе
    0.07
    ugged
    0.07
    Activations Density 0.012%

    No Known Activations