© 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. 10022
    Prev
    Next
    INDEX
    Explanations

    balance between

    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
    ä¸įåıªæĺ¯
    -0.10
    åħĪæĬĬ
    -0.10
    çĶļèĩ³è¿ĺ
    -0.09
    ä¸įä»ħ
    -0.09
    ä¸įåĥħ
    -0.08
    åħĪ
    -0.08
    ä¸įä½Ĩ
    -0.08
    èĢĹ
    -0.08
    ä»£æĽ¿
    -0.08
     sá»ķ
    -0.08
    POSITIVE LOGITS
    åıĪè¦ģ
    0.14
    åı¦ä¸Ģæĸ¹éĿ¢
    0.12
    æ¸´æľĽ
    0.11
    åħ¼é¡¾
    0.11
    æĹ¢è¦ģ
    0.10
    át
    0.10
    åıĪèĥ½
    0.09
    æĭ´
    0.09
    warts
    0.09
    顾
    0.09
    Activations Density 0.094%

    No Known Activations