© 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. 11855
    Prev
    Next
    INDEX
    Explanations

    kind of

    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
     volna
    -0.10
    ehme
    -0.10
    ting
    -0.10
    obod
    -0.10
    ároz
    -0.10
    Ø·ÙĨ
    -0.10
    оÑģÑĮ
    -0.10
    缸è¾ħ缸æĪIJ
    -0.10
    æĪĸå¤ļ个
    -0.09
    åIJĦç§įåIJĦæł·
    -0.09
    POSITIVE LOGITS
    ergarten
    0.08
    ous
    0.07
    ously
    0.07
    ement
    0.07
    ividual
    0.07
    -hearted
    0.06
    uct
    0.06
    ,
    0.06
    liness
    0.06
    ä¸Ĭè¿ĩ
    0.06
    Activations Density 0.071%

    No Known Activations