© 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. 35935
    Prev
    Next
    INDEX
    Explanations

    resize / sizing

    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
    åįģ足
    -0.10
    éĢĽ
    -0.10
    åħ³äºİæĪij们
    -0.10
    ä¸Ģå¤ľ
    -0.10
    ÅĤu
    -0.10
     üzerinde
    -0.10
    éĻįå¹ħ
    -0.09
    æ®Ħ
    -0.09
    å¤įåį°ä»¶
    -0.09
    /tos
    -0.09
    POSITIVE LOGITS
    移
    0.09
    许åı¯
    0.09
     \<
    0.08
    perm
    0.08
    ing
    0.08
    åIJİçļĦ
    0.08
    es
    0.08
    è¿İ
    0.08
    è¿ĩæĿ¥
    0.08
     Hav
    0.08
    Activations Density 0.139%

    No Known Activations