© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62550
    Prev
    Next
    INDEX
    Explanations

    describing bugs or issues

    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
    ittings
    -0.11
    å½±
    -0.09
    play
    -0.08
    á»Ī
    -0.08
    wei
    -0.08
    idual
    -0.08
    æĮģå¹³
    -0.08
    cott
    -0.08
    \Php
    -0.08
    olvers
    -0.08
    POSITIVE LOGITS
    çį¾
    0.10
    æĪ¢
    0.10
    å¸Ĥåİ¿
    0.10
    åīįæĻ¯
    0.09
    çĪ·çĪ·
    0.09
    åıªèĥ½è¯´
    0.09
    æľīä¿¡å¿ĥ
    0.09
    å¨ĥå¨ĥ
    0.09
    饱满
    0.09
    å¼ĢåıijåĪ©çĶ¨
    0.09
    Activations Density 0.005%

    No Known Activations