© 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. 21944
    Prev
    Next
    INDEX
    Explanations

    programming syntax and queries

    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
    acc
    -0.07
    éĤ¯éĥ¸
    -0.06
    å¢ŀåĢ¼
    -0.06
    éļIJ
    -0.06
    è¨
    -0.06
    å½±åĥı
    -0.06
    ...
    -0.06
     tast
    -0.06
     i
    -0.06
    ase
    -0.05
    POSITIVE LOGITS
    INLINE
    0.08
    ãĤ¯ãĥĪ
    0.08
    znÄĽ
    0.08
    idis
    0.08
    chetti
    0.08
    æ´Ľå¤«
    0.08
    é¾Ħ
    0.08
    opin
    0.08
     Haji
    0.07
    çĥı
    0.07
    Activations Density 0.006%

    No Known Activations