© 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. 7918
    Prev
    Next
    INDEX
    Explanations

    word endings like -st

    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
    Âł
    -0.07
    comings
    -0.07
    antis
    -0.06
    海滨
    -0.06
    or
    -0.06
    大åħ¸
    -0.06
    UAR
    -0.06
    ä¸įåIJĪ
    -0.06
    es
    -0.06
    天æĪIJ
    -0.06
    POSITIVE LOGITS
    tam
    0.08
    æĭīåħĭ
    0.08
    åĪ°å¤Ħ
    0.07
    ç§ģ人
    0.07
    -gnu
    0.07
    á»įc
    0.07
    /manual
    0.07
     McMaster
    0.07
    åİ»æīĵ
    0.07
    çŁ¥çļĦ
    0.07
    Activations Density 0.001%

    No Known Activations