© 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. 43628
    Prev
    Next
    INDEX
    Explanations

    counts, quantities, yield

    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
    ä¸įä½ıäºĨ
    -0.07
    IsRequired
    -0.07
    å±Ĥ
    -0.07
    shall
    -0.07
    dyn
    -0.07
    Layers
    -0.06
    .sigmoid
    -0.06
    stens
    -0.06
    æ¡£
    -0.06
     layered
    -0.06
    POSITIVE LOGITS
    æĢ»æķ°
    0.08
     counts
    0.08
     observed
    0.07
    ä¸Ģç»ıåıijçİ°
    0.07
    ingles
    0.07
    abeled
    0.07
    etton
    0.07
     totals
    0.07
    counts
    0.07
     Counts
    0.07
    Activations Density 0.002%

    No Known Activations