© 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. 39410
    Prev
    Next
    INDEX
    Explanations

    edited by, ed

    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
    è·Łè´´
    -0.09
    éĶ¦æ¶Ľ
    -0.08
    ÏĮδ
    -0.07
    ãĤĤãģ¨
    -0.07
    æĹ¥çĶµ
    -0.07
    mula
    -0.07
    边走
    -0.07
    à¸Ńà¸Ķี
    -0.07
    æijĩ
    -0.07
    çĤ¹ä¸ª
    -0.07
    POSITIVE LOGITS
    è¯įæĿ¡
    0.08
    elsey
    0.08
     Care
    0.07
    ed
    0.07
    rema
    0.07
    ess
    0.07
    adar
    0.07
    uce
    0.07
    omm
    0.07
    essa
    0.07
    Activations Density 0.050%

    No Known Activations