© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7411
    Prev
    Next
    INDEX
    Explanations

    xml version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åĵĩ
    -0.09
    åıŃ
    -0.08
    æĪIJ人
    -0.08
    ÙĤطع
    -0.08
    åĬ¡å·¥
    -0.08
    åħ¬çº¦
    -0.08
    è¡¥åĬ©
    -0.08
    大人
    -0.08
    åĵ©
    -0.07
    人åı£
    -0.07
    POSITIVE LOGITS
    é£İæݧ
    0.15
     securities
    0.14
     Securities
    0.13
    è¯ģåĪ¸
    0.12
    æĮģä»ĵ
    0.12
    è·¯æ¼Ķ
    0.12
    é£İéĻ©ç®¡çIJĨ
    0.12
    èµĦ管
    0.11
    æķ£æĪ·
    0.11
    沪深
    0.11
    Activations Density 0.610%

    No Known Activations