© 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. 42218
    Prev
    Next
    INDEX
    Explanations

    score in 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
    åݦ
    -0.08
     loạn
    -0.08
     _:
    -0.08
    ebro
    -0.07
    UPI
    -0.07
    entras
    -0.07
    fork
    -0.07
    Suit
    -0.07
    UNET
    -0.07
    /format
    -0.07
    POSITIVE LOGITS
    åį´èĥ½
    0.11
    åį´ä¾ĿçĦ¶
    0.10
    ä½Ĩåıªè¦ģ
    0.10
    åį´ä¹Ł
    0.09
    ä¸įè¿ĩåľ¨
    0.09
     Nevertheless
    0.09
    åį´æĺ¯
    0.09
     Nonetheless
    0.08
     unless
    0.08
     BUT
    0.08
    Activations Density 0.117%

    No Known Activations