© 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. 18500
    Prev
    Next
    INDEX
    Explanations

    company suffixes and locations

    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
    ç³»
    -0.07
    æĪijæŃ£åľ¨
    -0.06
    çŀij
    -0.06
    åĬªåĬĽåģļåĪ°
    -0.06
    /exp
    -0.06
    交éģĵ
    -0.06
    ä¸Ĭ没æľī
    -0.06
    æĭĹ
    -0.06
    ahn
    -0.06
    anan
    -0.06
    POSITIVE LOGITS
     Incorporated
    0.08
     주ìĭĿ
    0.08
    æľīéĻIJåħ¬åı¸
    0.08
     Pty
    0.08
     à¸Īำà¸ģัà¸Ķ
    0.08
     GmbH
    0.07
     Ltd
    0.07
    éĵ¶è¡ĮèĤ¡ä»½æľīéĻIJåħ¬åı¸
    0.07
    shine
    0.07
    .svg
    0.07
    Activations Density 0.379%

    No Known Activations