© 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. 33879
    Prev
    Next
    INDEX
    Explanations

    pd.Series or DataFrame definitions

    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
    åħ¨ä¼ļ
    -0.06
    uns
    -0.06
    ette
    -0.06
    hiba
    -0.06
    OTA
    -0.06
    ura
    -0.06
    loy
    -0.06
    å¹¶è¿Ľ
    -0.06
    è¿ĺæľīä¸ĢçĤ¹
    -0.06
    cho
    -0.06
    POSITIVE LOGITS
    åı¦
    0.09
    åı¦ä¸Ģ
    0.09
     another
    0.09
    another
    0.08
    åı¦ä¸Ģæĸ¹
    0.08
    çĿ¿
    0.08
    åı¦ä¸ĢåĢĭ
    0.07
    åıĪä¸Ģ
    0.07
    ä¸ĢæĪ·
    0.07
     MIS
    0.07
    Activations Density 0.350%

    No Known Activations