© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14662
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    cker
    -0.08
    icie
    -0.08
    elj
    -0.07
    anton
    -0.07
    itzen
    -0.07
    ovich
    -0.07
    /utility
    -0.07
    TokenType
    -0.07
    rigen
    -0.07
    apol
    -0.07
    POSITIVE LOGITS
    Gam
    0.07
     Gam
    0.07
    einander
    0.07
     gam
    0.07
    elter
    0.07
    \<
    0.07
    -done
    0.07
    resh
    0.06
    æį®æĬ¥éģĵ
    0.06
     Abd
    0.06
    Activations Density 0.218%

    No Known Activations