© 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. 36161
    Prev
    Next
    INDEX
    Explanations

    mandatory

    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
    avit
    -0.10
    ormal
    -0.10
    canf
    -0.09
    COMMON
    -0.09
    idor
    -0.09
    åīįæīĢ
    -0.09
    ä¸į大
    -0.09
    ä¸įåĩºæĿ¥
    -0.09
    大æĪĺ
    -0.09
    ãģ¤ãĤĤãĤĬ
    -0.09
    POSITIVE LOGITS
    æĢ§å¼º
    0.12
    ìĤ¬íķŃ
    0.11
    ities
    0.11
    æĢ§çļĦ
    0.10
    ity
    0.10
    mente
    0.09
     ByVal
    0.09
     kèm
    0.09
    ITY
    0.08
     preceding
    0.08
    Activations Density 0.025%

    No Known Activations