© 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. 49075
    Prev
    Next
    INDEX
    Explanations

    doesn't make sense

    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
    ä¸įå¾Ĺå·²
    -0.07
    agas
    -0.07
    commons
    -0.07
    æħİéĩį
    -0.06
    arz
    -0.06
     Pere
    -0.06
    å¹²èĦĨ
    -0.06
    à¸Ńà¸Ķ
    -0.06
    EGI
    -0.06
    opal
    -0.06
    POSITIVE LOGITS
    并ä¸įæĦıåij³çĿĢ
    0.14
    并ä¸į代表
    0.12
    ä¸į代表
    0.12
    å°±ä¸Ģå®ļ
    0.10
    ä¹Łå¹¶ä¸į
    0.10
     necessarily
    0.09
    ä¸įçŃīäºİ
    0.09
    ä»»ä½ķäºĭæĥħ
    0.08
    ä»įéľĢ
    0.08
    ä¹Łä¸įä¸Ģå®ļ
    0.08
    Activations Density 0.072%

    No Known Activations