© 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. 5784
    Prev
    Next
    INDEX
    Explanations

    Kanye West, teeth

    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
    å¸ĥæĭī
    -0.10
    بش
    -0.10
    积
    -0.09
    éĵ
    -0.09
    嬷
    -0.09
    ष
    -0.08
    çīµæĮĤ
    -0.08
    -expanded
    -0.08
    积累
    -0.08
    imat
    -0.08
    POSITIVE LOGITS
     зÑĢ
    0.10
    åŃ³
    0.09
    _$_
    0.09
    ä¸ĢæĶ¯
    0.09
    æľīåĬ©
    0.09
    éķ¿æ²Ļ
    0.09
    ategy
    0.08
    ä¸Ģ举
    0.08
     deb
    0.08
    eks
    0.08
    Activations Density 0.011%

    No Known Activations