© 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. 32290
    Prev
    Next
    INDEX
    Explanations

    connecting clauses and phrases

    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
    SRC
    -0.07
    ç¿
    -0.07
    æĸ°å¤©åľ°
    -0.06
    onie
    -0.06
    plet
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    åĴĮä¸į
    -0.06
    Do
    -0.06
     overt
    -0.06
    onii
    -0.06
    POSITIVE LOGITS
    åıįä¹ĭ
    0.09
    fds
    0.09
    getc
    0.08
    æĺ¯ä¸ĢåĪĩ
    0.08
    ä½ķåĨµ
    0.08
    antum
    0.08
    ilon
    0.07
    å·§
    0.07
    olgen
    0.07
     vice
    0.07
    Activations Density 0.098%

    No Known Activations