© 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. 53392
    Prev
    Next
    INDEX
    Explanations

    connected or placed in a state

    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
     Fulton
    -0.11
    ä¸Ģä¸ĭ
    -0.11
     Whip
    -0.10
    åijĹ
    -0.10
    æݧ
    -0.10
    ä¸Ģ次æĢ§
    -0.09
    æĻºåķĨ
    -0.09
    .len
    -0.09
    ä¸Ģä¸ĭåŃIJ
    -0.09
    ä¸ĢåĪĢ
    -0.09
    POSITIVE LOGITS
    ited
    0.11
    çĬ¶æĢģä¸ĭ
    0.10
    ness
    0.10
    ated
    0.09
     Dunn
    0.09
     ìĥģíĥľ
    0.09
    åIJİçļĦ
    0.09
    说çļĦæĺ¯
    0.09
    çĬ¶æĢģ
    0.08
    çļĦçĬ¶æĢģ
    0.08
    Activations Density 0.229%

    No Known Activations