© 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. 7397
    Prev
    Next
    INDEX
    Explanations

    library catalog/reference

    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
    å¼ķ
    -0.07
    æĸĩç¬Ķ
    -0.07
    gemeinde
    -0.07
    è¾¾
    -0.07
    isme
    -0.07
    iskan
    -0.07
     virgin
    -0.06
    åŀ
    -0.06
    EMY
    -0.06
    à¸Ľà¸ıิà¸ļัà¸ķิ
    -0.06
    POSITIVE LOGITS
    éļ¾
    0.08
    å¥
    0.07
    çİīå±±
    0.07
    rest
    0.07
    æīĵéĢłæĪIJ
    0.07
    æķħåIJį
    0.06
    æīįæĺ¯çľŁæŃ£çļĦ
    0.06
     realis
    0.06
    alu
    0.06
    OrFail
    0.06
    Activations Density 0.002%

    No Known Activations