© 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. 65205
    Prev
    Next
    INDEX
    Explanations

    explaining or describing

    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
    whose
    -0.08
     cuja
    -0.08
    insky
    -0.08
     cujo
    -0.08
     whose
    -0.08
     cuyo
    -0.08
     cuya
    -0.08
     Ejem
    -0.08
    ä½łè¯´çļĦ
    -0.07
    æĪĸåľ¨
    -0.07
    POSITIVE LOGITS
    :
    0.11
    å¦Ĥä¸ĭ
    0.11
    à¸Ķัà¸ĩà¸Ļีà¹ī
    0.09
    ï¼ļ
    0.08
    以ä¸ĭåĩłçĤ¹
    0.08
    åľ¨äºİ
    0.08
    å§ĭäºİ
    0.08
     follows
    0.07
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.07
     centered
    0.07
    Activations Density 0.057%

    No Known Activations