© 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. 55391
    Prev
    Next
    INDEX
    Explanations

    but not

    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
    ning
    -0.09
    ç½ijç«Ļ导èĪª
    -0.08
    ä¸įä»İ
    -0.08
    éĵ¿
    -0.08
    ä¸įå¿ĺ
    -0.08
    isted
    -0.08
    ä¸įåĬ¨æijĩ
    -0.08
     íĭĢ
    -0.08
    ä¸įæIJŀ
    -0.08
    çļĦä»»ä½ķ
    -0.07
    POSITIVE LOGITS
     simply
    0.08
     a
    0.08
     something
    0.08
    ãĤĢãģĹãĤį
    0.07
    ...
    0.07
     an
    0.07
     indeed
    0.07
     наобоÑĢоÑĤ
    0.07
    âĢ¦
    0.07
    ...]
    0.07
    Activations Density 0.039%

    No Known Activations