© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11786
    Prev
    Next
    INDEX
    Explanations

    haptic devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    iếc
    -0.21
    ETHER
    -0.19
     ;;=
    -0.18
    KEN
    -0.17
    ivol
    -0.17
    à¹ĥ
    -0.17
    çºĮ
    -0.16
    ×¢×ŀ×ķ×ĵ
    -0.16
     ;;^
    -0.16
    roperty
    -0.16
    POSITIVE LOGITS
    ç¥ļ
    0.23
    裸
    0.21
    æĿŀ
    0.21
     Naked
    0.21
    åĩºåĽ½çķĻåѦ
    0.18
    çļĦç¾İ好
    0.18
    èĴ¯
    0.18
    èµı
    0.17
     Bá
    0.17
    nelle
    0.17
    Activations Density 0.596%

    No Known Activations