© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15092
    Prev
    Next
    INDEX
    Explanations

    HTML entities and tags

    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
    çļĦä¸Ģçŀ¬éĹ´
    -0.07
    িদ
    -0.07
    landet
    -0.07
    àµį
    -0.07
    绸
    -0.06
    æµ·è§Ĵ
    -0.06
    otti
    -0.06
    hood
    -0.06
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    -0.06
    为大家ä»ĭç»į
    -0.06
    POSITIVE LOGITS
    Ĵ
    0.08
    anke
    0.08
    áĢ®áĢ¸
    0.08
    Ķ
    0.07
    ARY
    0.07
     few
    0.07
    icina
    0.07
    å°ijæķ°
    0.07
    znam
    0.07
    ¢
    0.06
    Activations Density 0.005%

    No Known Activations