© 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. 15445
    Prev
    Next
    INDEX
    Explanations

    official announcements and public records

    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
    çĽ¸ä¼ł
    -0.07
    æ¬łç¨İåħ¬åijĬ
    -0.07
     Sylv
    -0.06
    çľģå§Ķ书记
    -0.06
    reed
    -0.06
    丢
    -0.06
     Donn
    -0.06
     Pan
    -0.06
    强éĻ©
    -0.06
    æī§çħ§
    -0.06
    POSITIVE LOGITS
    ä¿¡æģ¯æĬ«éľ²
    0.10
    åĭ¤åĭī
    0.10
    æĬ«éľ²
    0.09
    ivid
    0.09
    çĢļ
    0.08
    çĴŀ
    0.08
    åĭŁéĽĨèµĦéĩij
    0.08
    åľ¨æľ¬æ¬¡
    0.08
    IPO
    0.08
    Fetcher
    0.08
    Activations Density 0.015%

    No Known Activations