© 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. 22121
    Prev
    Next
    INDEX
    Explanations

    in addition to

    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
    è¦ģä¹Ī
    -0.11
    éĢ¢
    -0.09
    (exc
    -0.09
    ä¸ºæľŁ
    -0.09
    ersistence
    -0.09
    äºİæĺ¯
    -0.09
    å¾¼
    -0.08
    éªŀ
    -0.08
     Kate
    -0.08
    Kate
    -0.08
    POSITIVE LOGITS
    è¿ĺæľīä¸Ģ个
    0.10
    è¿ĺæľī
    0.10
    ä¹ĭå¤ĸ
    0.10
    æĻºåĬĽ
    0.10
    æĦıå¤ĸ
    0.09
    åħ¶å®ĥ
    0.09
    è¿ĺè¦ģ
    0.09
    éľĢè¦ģ注æĦı
    0.09
    è¿ĺæĥ³
    0.09
    æľīåĩłä¸ª
    0.09
    Activations Density 0.031%

    No Known Activations