© 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. 31468
    Prev
    Next
    INDEX
    Explanations

    time, again, second

    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
    gens
    -0.07
    涮
    -0.07
    ÑĢод
    -0.06
     Fisc
    -0.06
    å¤ĸéĵ¾
    -0.06
     aina
    -0.06
    ieza
    -0.06
    ä½łè¿ĺåľ¨
    -0.06
    çĽ
    -0.06
    STYLE
    -0.06
    POSITIVE LOGITS
     Again
    0.12
     again
    0.12
    Again
    0.11
    again
    0.11
    åıĪæĺ¯ä¸Ģ个
    0.09
    åĨįãģ³
    0.08
     erneut
    0.08
     nuevamente
    0.08
    第ä¸ī个
    0.08
    ãģĵãģ¡ãĤīãĤĤ
    0.08
    Activations Density 0.108%

    No Known Activations