© 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. 58364
    Prev
    Next
    INDEX
    Explanations

    a quantity or characteristic

    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»»ä½ķäºĭæĥħ
    -0.09
    _EXTERN
    -0.09
    çļĦäºĭæĥħäºĨ
    -0.09
    ä¸Ģè¶Ł
    -0.08
    åı¦æľī
    -0.08
    大èĥľ
    -0.08
    çļĦäºĭäºĨ
    -0.08
    éĩįä¸Ńä¹ĭéĩį
    -0.08
    สำà¸Ħัà¸įà¸Ĥà¸Ńà¸ĩ
    -0.08
    åİ®
    -0.08
    POSITIVE LOGITS
     been
    0.10
    ered
    0.09
    åıĤèĢĥä»·åĢ¼
    0.08
     characteristics
    0.08
    èĩªå·±çļĦ
    0.08
     undergone
    0.07
     varying
    0.07
     sido
    0.07
    缸åIJĮ
    0.07
    ering
    0.07
    Activations Density 0.308%

    No Known Activations