© 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. 32126
    Prev
    Next
    INDEX
    Explanations

    parts per million or percent

    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
    izoph
    -0.07
    axter
    -0.07
    neur
    -0.06
     knocked
    -0.06
     angered
    -0.06
    ³
    -0.06
    jed
    -0.06
    ÅĪ
    -0.06
    eschi
    -0.06
    çļĦ建设
    -0.06
    POSITIVE LOGITS
    alth
    0.08
    èĢĮèµ°
    0.07
    alej
    0.07
    abit
    0.07
    ayos
    0.07
    ettava
    0.07
    级çļĦ
    0.07
    äºĮæĺ¯è¦ģ
    0.07
    ç»ĻæĪijçķĻè¨Ģ
    0.07
    rato
    0.07
    Activations Density 0.001%

    No Known Activations