© 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. 11140
    Prev
    Next
    INDEX
    Explanations

    Wires and dates

    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
    oplast
    -0.07
    çļĦä¸įèī¯
    -0.06
     magna
    -0.06
    عب
    -0.06
    è¿ľæµģ
    -0.06
    RF
    -0.06
    ogat
    -0.06
    æ²½
    -0.06
    жи
    -0.06
    ĮĢ
    -0.06
    POSITIVE LOGITS
    acol
    0.08
    roph
    0.08
    尿裤
    0.08
    æļ§
    0.08
     dope
    0.08
    _HAL
    0.08
    enske
    0.08
    æĸ°æµªç½ij
    0.08
    endr
    0.08
    çĻ¾æĹ¥
    0.07
    Activations Density 0.024%

    No Known Activations