© 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. 55752
    Prev
    Next
    INDEX
    Explanations

    waiting, learning, loudspeaker, surrounding, Warning

    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
    ạnh
    -0.07
    ãģ®ãĤĤãģ®
    -0.07
    intang
    -0.07
    éĤ£ä¹Īå¤ļ
    -0.07
    æĺ¯åħ¶
    -0.07
    ulli
    -0.07
    åı¤å±ĭ
    -0.07
    _en
    -0.06
    XT
    -0.06
    æĽ¾è¯´è¿ĩ
    -0.06
    POSITIVE LOGITS
    ä¸įè¾ŀ
    0.07
    eson
    0.07
    ÑĢем
    0.07
    ä¸į欲
    0.07
    lem
    0.06
    adó
    0.06
    å½Ĵæł¹
    0.06
    ]+\
    0.06
    çIJĽ
    0.06
    itled
    0.06
    Activations Density 0.001%

    No Known Activations