© 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. 27054
    Prev
    Next
    INDEX
    Explanations

    variables and parameters

    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
    åĤ²
    -0.07
    弯弯
    -0.07
    æ¡£
    -0.06
     Dres
    -0.06
    ITAR
    -0.06
    [][
    -0.06
     HACK
    -0.06
    поÑĢ
    -0.06
    IBC
    -0.06
    æ¸Ŀ
    -0.06
    POSITIVE LOGITS
    æĺ¯åħ¶
    0.07
    icz
    0.07
    orman
    0.07
    å¿Į
    0.07
    æĪij们ä¼ļ尽快
    0.07
    otten
    0.07
    lden
    0.07
    ame
    0.06
    ä¸Ńåħ¬
    0.06
    usche
    0.06
    Activations Density 0.034%

    No Known Activations