© 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. 42695
    Prev
    Next
    INDEX
    Explanations

    avoiding specific items

    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
    èĢĮéĿŀ
    -0.07
    没éĤ£ä¹Ī
    -0.07
    ä¸įæĥ§
    -0.07
    没æľīéĤ£ä¹Ī
    -0.07
    并ä¸įéļ¾
    -0.07
     mẽ
    -0.07
    å¾Ĺèµ·
    -0.07
    ç¨ĭ
    -0.06
    ä¸įæŀĦæĪIJ
    -0.06
    æĻĵ
    -0.06
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ıçļĦ
    0.16
    ä¹Łä¸įè¦ģ
    0.15
    以åħįéĢłæĪIJ
    0.14
    以åħįå½±åĵį
    0.14
    æľīä»»ä½ķ
    0.13
    à¹Ģà¸Ķà¹ĩà¸Ķ
    0.13
    以åħį
    0.13
    çļĦä»»ä½ķ
    0.13
    æĽ´ä¸įè¦ģ
    0.13
    以任ä½ķ
    0.13
    Activations Density 0.054%

    No Known Activations