© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52157
    Prev
    Next
    INDEX
    Explanations

    more tranquil, want, worried

    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
    涯
    -0.10
    讶
    -0.09
    é«ĺç´łè´¨
    -0.09
     Fernando
    -0.09
    Breadcrumb
    -0.09
    忤
    -0.09
    客æ°Ķ
    -0.09
    èĩ³å°ij
    -0.08
    è¿©
    -0.08
    æŃ£å¸¸ä½¿çĶ¨
    -0.08
    POSITIVE LOGITS
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    0.10
    ãĤĤãģ£ãģ¨
    0.10
    ãģķãĤīãģ«
    0.09
    æĽ´ä¸º
    0.09
    åħ¬ç«ł
    0.09
     напÑĢавлен
    0.09
    åı¦ä¸Ģç§į
    0.09
    è¿ĺæľīä¸ĢäºĽ
    0.09
    æĽ´åħ·
    0.09
    代表æĢ§
    0.08
    Activations Density 0.053%

    No Known Activations