© 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. 42550
    Prev
    Next
    INDEX
    Explanations

    to convert

    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
     theirs
    -0.07
    engah
    -0.07
    _CAST
    -0.07
    éĥ½ä¸įéĶĻ
    -0.07
    åIJ¦åĪĻ
    -0.07
    宣称
    -0.07
    ä¸įçĦ¶
    -0.07
    æĹłè®ºæĺ¯
    -0.07
     &[
    -0.06
    ä¸į论æĺ¯
    -0.06
    POSITIVE LOGITS
    abus
    0.07
    uya
    0.07
    robe
    0.07
    .INSTANCE
    0.07
    oyer
    0.07
    ptype
    0.07
     tqdm
    0.06
    Ùħاس
    0.06
     
    0.06
    ôi
    0.06
    Activations Density 0.001%

    No Known Activations