© 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. 28607
    Prev
    Next
    INDEX
    Explanations

    code syntax delimiters

    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
    åĶ¯ä¸Ģä¸Ģ家
    -0.08
    .ini
    -0.07
    oken
    -0.07
    ?action
    -0.07
    åıĸãĤĬæī±ãģĦ
    -0.07
    ackbar
    -0.07
    åħī顾
    -0.07
    ãģĿãĤĤ
    -0.07
    .jsp
    -0.07
    .charCodeAt
    -0.07
    POSITIVE LOGITS
    mmas
    0.07
     syl
    0.07
    æݨçIJĨ
    0.07
    åĩ¡äºĭ
    0.07
    fold
    0.07
     proofs
    0.07
     abstract
    0.07
    actic
    0.06
     Fold
    0.06
    æĬ½è±¡
    0.06
    Activations Density 0.025%

    No Known Activations