© 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. 40013
    Prev
    Next
    INDEX
    Explanations

    numbers or punctuation followed by text

    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
     ار
    -0.07
    è¬
    -0.07
    æĮģåį¡
    -0.07
    èį·è½½
    -0.07
    оÑĤÑĮ
    -0.06
    anat
    -0.06
    oldt
    -0.06
    سط
    -0.06
    otá
    -0.06
    olog
    -0.06
    POSITIVE LOGITS
    ä¸ĩå²ģ
    0.07
    çļĦåģļæ³ķ
    0.07
    æ±Ĥè´Ń
    0.07
    ä¸Ģèĩ´è®¤ä¸º
    0.07
     cases
    0.07
    andi
    0.07
    é¢ĺ为
    0.07
    æĥħåĨµè¿Ľè¡ĮäºĨ
    0.07
    works
    0.07
     menda
    0.07
    Activations Density 0.553%

    No Known Activations