© 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. 20424
    Prev
    Next
    INDEX
    Explanations

    short or long descriptions

    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
    æ¯ĽéĴ±
    -0.07
    ogna
    -0.07
    å¾Ī强çļĦ
    -0.07
    纵
    -0.07
    临
    -0.07
    mond
    -0.07
    iya
    -0.06
    nelly
    -0.06
    ibs
    -0.06
    ixin
    -0.06
    POSITIVE LOGITS
    ITED
    0.07
    Indexed
    0.07
    å°½éĩıå°ij
    0.07
     susc
    0.07
     Ob
    0.07
    Äĥr
    0.07
    ÄĥrÄĥ
    0.07
    arli
    0.07
    arei
    0.06
    ī
    0.06
    Activations Density 0.004%

    No Known Activations