© 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. 32034
    Prev
    Next
    INDEX
    Explanations

    removing or stopping something

    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
    åľŁè±ª
    -0.11
    çĵ®
    -0.09
     cres
    -0.09
    æĭ½
    -0.08
     Zub
    -0.08
    æĥħå½¢
    -0.08
    年产
    -0.08
    çļij
    -0.08
    æħķ
    -0.08
    luet
    -0.08
    POSITIVE LOGITS
    ä¸į顾
    0.10
    æľ¬æĿ¥
    0.10
    æ®Ĩ
    0.09
    inn
    0.09
    åİŁæľīçļĦ
    0.09
    æľīä»·åĢ¼çļĦ
    0.09
    åĩ¡
    0.09
    å½»åºķ
    0.08
    ael
    0.08
    ä»»ä½ķ
    0.08
    Activations Density 0.085%

    No Known Activations