© 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. 28243
    Prev
    Next
    INDEX
    Explanations

    average measurement or size

    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
    ehl
    -0.08
    kis
    -0.08
    elis
    -0.08
    ahr
    -0.08
    actus
    -0.08
    ney
    -0.08
    æĪ¿å±ĭ秣èµģ
    -0.08
    edale
    -0.08
    edt
    -0.08
    UBLE
    -0.07
    POSITIVE LOGITS
    å¹³åĿĩ
    0.08
     average
    0.07
    average
    0.07
    å¹³åĿĩæ¯ı
    0.07
    çļĦå¹³åĿĩ
    0.07
     avg
    0.06
    utin
    0.06
    Average
    0.06
    Stamped
    0.06
     اÙĦÙĪاØŃد
    0.06
    Activations Density 0.036%

    No Known Activations