© 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. 37647
    Prev
    Next
    INDEX
    Explanations

    surnames ending in i/y/ski/rians/baugh

    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
    嵩
    -0.10
    erah
    -0.09
    aldi
    -0.09
    å¥ĭæĸĹ缮æłĩ
    -0.09
    ä¸ĢæĬ¹
    -0.09
    è¿ĺ以为
    -0.08
     outs
    -0.08
    æ°Ķ象
    -0.08
    çļĦæĦŁåıĹ
    -0.08
    blade
    -0.08
    POSITIVE LOGITS
    æ¡ĥ
    0.10
    离
    0.10
    åį·
    0.09
    éĽ¢
    0.09
    avy
    0.09
    éĢīæīĭ
    0.09
    owan
    0.08
    éĶĻè¿ĩ
    0.08
    _lift
    0.08
    è¿Ļ段
    0.08
    Activations Density 0.006%

    No Known Activations