© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26478
    Prev
    Next
    INDEX
    Explanations

    Gaussian beam, compartment, network, assume

    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
    ronym
    -0.08
     Alfon
    -0.07
    زÙħ
    -0.07
    ä»İåĵªéĩĮ
    -0.07
    ERO
    -0.07
    encers
    -0.07
    辦æ³ķ
    -0.07
    runtime
    -0.07
    ä»Ģ
    -0.07
     renomm
    -0.07
    POSITIVE LOGITS
    åģĩ设
    0.12
     assumed
    0.11
    assume
    0.10
    åģĩå®ļ
    0.09
     Assume
    0.09
    模åŀĭ
    0.09
     modeled
    0.09
     assumptions
    0.09
     assuming
    0.09
     assume
    0.09
    Activations Density 0.372%

    No Known Activations