© 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. 50622
    Prev
    Next
    INDEX
    Explanations

    known as / formerly

    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
    lander
    -0.07
    ä¸įèĩ³
    -0.07
    Ñĭл
    -0.07
    设计ä¸Ĭ
    -0.07
    boa
    -0.07
    lal
    -0.07
    ÑĥÑĤа
    -0.06
     priz
    -0.06
    æ¯ĶæĻ®éĢļ
    -0.06
    åĬ¨
    -0.06
    POSITIVE LOGITS
    aka
    0.08
    åıĪåIJį
    0.08
    åħīèį£
    0.07
     tro
    0.07
     synonymous
    0.07
     Tro
    0.07
    roud
    0.07
    åİŁåIJį
    0.06
    HP
    0.06
     Caucus
    0.06
    Activations Density 0.194%

    No Known Activations