© 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. 55700
    Prev
    Next
    INDEX
    Explanations

    white blood cell counts

    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
    lern
    -0.08
    æľĢ大åĬŁçİĩ
    -0.07
     undermin
    -0.06
    iste
    -0.06
    纬
    -0.06
    iane
    -0.06
    èĭĵ
    -0.06
    /feed
    -0.06
    éĥijéĩį声æĺİ
    -0.06
     implicitly
    -0.06
    POSITIVE LOGITS
    æĢ»æķ°
    0.12
    æĢ»æķ°çļĦ
    0.09
     counts
    0.09
    counts
    0.09
    ãģ®æĹħ
    0.08
     Counts
    0.08
    çĻ½ç»Ĩèĥŀ
    0.08
    numbers
    0.08
    Counts
    0.08
    Numbers
    0.08
    Activations Density 0.116%

    No Known Activations