© 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. 3877
    Prev
    Next
    INDEX
    Explanations

    any other size for that matter

    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´¯
    -0.10
    æĪĸå°Ĩ
    -0.10
    è°Ĵ
    -0.09
    å¨ĥå¨ĥ
    -0.09
    Hdr
    -0.09
    éĢĤå½ĵ
    -0.09
    ä¾®
    -0.09
    貫
    -0.08
    å¤įåį°ä»¶
    -0.08
    好åIJ§
    -0.08
    POSITIVE LOGITS
    æ¬ł
    0.09
    ODY
    0.09
    æĺ¯ä¸Ģ件
    0.08
    oad
    0.08
    çīį
    0.08
    éĶ¦ç»£
    0.08
    åĨı
    0.08
    C
    0.08
    丢
    0.08
    oke
    0.08
    Activations Density 0.138%

    No Known Activations