© 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. 5720
    Prev
    Next
    INDEX
    Explanations

    consideration

    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
    oins
    -0.10
    â½Ģ
    -0.09
    æĪĺæĸĹ
    -0.09
     acomp
    -0.09
    æijĩ
    -0.09
    æľīæĿ¡ä»¶çļĦ
    -0.09
    精彩çļĦ
    -0.08
    æĪĸå¤ļ
    -0.08
    æĶ»åħ³
    -0.08
    æĭ¥æĬ¤
    -0.08
    POSITIVE LOGITS
    åĽłç´ł
    0.22
    çļĦåĽłç´ł
    0.19
    èĢĥèĻij
    0.19
    è¦ģèĢĥèĻij
    0.16
     factors
    0.16
    èĢĥæħ®
    0.15
    èĢĥéĩı
    0.15
    çŃīåĽłç´ł
    0.14
     considerations
    0.13
     consider
    0.12
    Activations Density 0.211%

    No Known Activations