© 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. 3452
    Prev
    Next
    INDEX
    Explanations

    checking, asking

    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
    éŀ
    -0.08
    akis
    -0.07
    ali
    -0.07
    ingers
    -0.06
    ariat
    -0.06
    ajt
    -0.06
    èĨ
    -0.06
    åĭĭ
    -0.06
    被æĴŀ
    -0.06
    èĤ¥
    -0.06
    POSITIVE LOGITS
    oppi
    0.08
     Sudoku
    0.08
     sudoku
    0.08
    æľ¬å¸ĸ
    0.08
    ĥĿ
    0.08
    âĸ·
    0.08
    åıĸæ¶Īåħ¶
    0.07
    æ±Ĥç²¾
    0.07
    лÑĮко
    0.07
    è¿«
    0.07
    Activations Density 0.008%

    No Known Activations