© 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. 27542
    Prev
    Next
    INDEX
    Explanations

    sea snail

    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
    indert
    -0.07
    ivant
    -0.06
     dedicate
    -0.06
     ÑģÑİ
    -0.06
    RIES
    -0.06
    ryo
    -0.06
    åĢ¼å¾ĹæĪij们
    -0.06
    -inc
    -0.06
    æľīå¾ħ
    -0.06
    stva
    -0.06
    POSITIVE LOGITS
    å±ŀäºİ
    0.19
    å±ŀ
    0.16
    屬æĸ¼
    0.16
    è¿Ļæĺ¯ä¸Ģ个
    0.14
    屬
    0.14
    å®ĥæĺ¯ä¸Ģ个
    0.14
    —an
    0.14
    —a
    0.14
    è¿Ļæĺ¯ä¸ª
    0.14
    à¸ĭึà¹Īà¸ĩà¹Ģà¸Ľà¹ĩà¸Ļ
    0.14
    Activations Density 0.305%

    No Known Activations