© 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. 48535
    Prev
    Next
    INDEX
    Explanations

    publicly available

    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
    身边
    -0.11
    åŃ½
    -0.10
    å¿«æĬ¥
    -0.09
     parad
    -0.09
    身边çļĦ
    -0.09
    æ¦
    -0.09
    èįij
    -0.09
    éĥħ
    -0.08
    åºĵéĩĮ
    -0.08
    ulla
    -0.08
    POSITIVE LOGITS
    åħ¬å¼Ģ
    0.27
    åħ¬éĸĭ
    0.21
    åħ¬å¼Ģåıij
    0.20
    åħ¬çĦ¶
    0.19
     publicly
    0.18
    ä¿¡æģ¯åħ¬å¼Ģ
    0.12
    åħ¬ä¼Ĺ
    0.12
    .public
    0.11
    (public
    0.11
     openly
    0.11
    Activations Density 0.119%

    No Known Activations