© 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. 62718
    Prev
    Next
    INDEX
    Explanations

    orbital orientation and configuration

    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
     logged
    -0.07
     corrid
    -0.07
    Iterations
    -0.07
    椿
    -0.07
    ÙĦاÙĨ
    -0.06
     tiers
    -0.06
    ÑģÑĤÑĸ
    -0.06
    edd
    -0.06
     unic
    -0.06
    çĽ¸ä¿¡æĪij
    -0.06
    POSITIVE LOGITS
     corresponds
    0.07
    udas
    0.07
    笼
    0.07
     Mapping
    0.07
     orient
    0.07
     vector
    0.07
    对åºĶ
    0.07
    æĺ¯å±ŀäºİ
    0.07
     Vector
    0.07
     mapping
    0.06
    Activations Density 0.001%

    No Known Activations