© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1607
    Prev
    Next
    INDEX
    Explanations

    USB ports and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gerr
    -0.26
    season
    -0.25
     factual
    -0.25
     divert
    -0.24
    à¹Ĥà¸Ĩ
    -0.24
    ãĥįãĤ¿
    -0.24
    greens
    -0.23
    andering
    -0.23
    habit
    -0.23
     Voices
    -0.23
    POSITIVE LOGITS
    åħ¼å®¹
    0.51
     ports
    0.48
    æİ¥åı£
    0.43
    -compatible
    0.39
     port
    0.38
    è¿ŀæİ¥
    0.38
     socket
    0.38
     compatible
    0.38
     USB
    0.37
     compatibility
    0.37
    Activations Density 0.077%

    No Known Activations