© 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. 994
    Prev
    Next
    INDEX
    Explanations

    symbols and numbers within parentheses

    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
    麻麻
    -0.06
    å¦ĤçĶ»
    -0.06
     automatic
    -0.06
    MESS
    -0.06
    "],"
    -0.06
    TemplateName
    -0.06
    -en
    -0.06
    èµ°è¿ĩåİ»
    -0.06
    è£ĺ
    -0.06
    æѤä¸Ģ
    -0.06
    POSITIVE LOGITS
    hofer
    0.07
    ansir
    0.07
    ä¸įåħ¥
    0.07
     appunto
    0.07
    HeaderCode
    0.07
    ç¼ķ
    0.07
    ower
    0.07
    arel
    0.07
    ä¸īä¸ĥ
    0.07
    ahre
    0.07
    Activations Density 0.278%

    No Known Activations