© 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. 20053
    Prev
    Next
    INDEX
    Explanations

    targets and hosts

    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
    å½±å±ķ
    -0.07
    ä½ľä¸ºä¸Ģ项
    -0.07
    vÃŃo
    -0.07
    è¿Ļæĺ¯å¯¹
    -0.07
    /misc
    -0.06
    ä½ľä¸ºä¸Ģç§į
    -0.06
    çĶ¨è¯Ń
    -0.06
    ä¹Łæĺ¯è¿Ļæł·
    -0.06
    ioni
    -0.06
    ÑĪне
    -0.06
    POSITIVE LOGITS
    ä¹ĭä¸ĢçļĦ
    0.16
     berupa
    0.12
    ä¹ĭä¸Ģ
    0.10
    活水
    0.10
    ä¹ĭä¸Ģæĺ¯
    0.10
    /source
    0.10
    ãģ¨ãģªãĤĭ
    0.09
    less
    0.09
    ä¸įæĺİçļĦ
    0.09
    ä¹ĭä¸Ģå°±æĺ¯
    0.09
    Activations Density 0.458%

    No Known Activations