© 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. 20492
    Prev
    Next
    INDEX
    Explanations

    elliptic curve

    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
     Alps
    -0.07
    夹
    -0.07
    ç½
    -0.07
    大èĩªçĦ¶
    -0.07
    å¿ĥäºĨ
    -0.07
    å¦Ĥå±±
    -0.07
    符
    -0.06
    åĨĽè®Ń
    -0.06
     Prat
    -0.06
    éĩĩ
    -0.06
    POSITIVE LOGITS
     ellipt
    0.10
    omorphic
    0.08
    ÃŃticas
    0.08
    รัà¸ķà¸Ļ
    0.08
    è¨Ĺ
    0.07
    unku
    0.07
     financi
    0.07
    å¤§åľ£
    0.07
    åIJ¸å¼ķäºĨä¼Ĺå¤ļ
    0.07
    ÃŃg
    0.07
    Activations Density 0.009%

    No Known Activations