© 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. 39565
    Prev
    Next
    INDEX
    Explanations

    all matrices and sets

    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
    缴è¾ĸ
    -0.07
    abin
    -0.07
    ģ
    -0.07
    saf
    -0.07
    建设æĪIJ为
    -0.07
    æ¦Ħ
    -0.06
    oho
    -0.06
    .dict
    -0.06
    uling
    -0.06
    mage
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.10
    (other
    0.08
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.08
    ä»»ä½ķåħ¶ä»ĸ
    0.08
    çļĦåħ¶ä»ĸ
    0.08
    (compare
    0.08
    another
    0.08
     comparison
    0.08
    æ¯Ķä»ĸ
    0.08
    åIJĮç±»
    0.08
    Activations Density 0.008%

    No Known Activations