© 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. 18749
    Prev
    Next
    INDEX
    Explanations

    never before, previously undescribed

    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
    åħį
    -0.09
     mo
    -0.09
    é£İçŃĿ
    -0.09
    éĻŁ
    -0.09
    欢快
    -0.09
    æij©
    -0.09
    çī¤
    -0.08
    åıįèĢĮ
    -0.08
     offending
    -0.08
     Mo
    -0.08
    POSITIVE LOGITS
    åīįæīĢæľª
    0.19
    ä»İæľª
    0.18
    åīįæīĢæľªæľī
    0.17
    ä»İæĿ¥æ²¡æľī
    0.16
    æľªæĽ¾
    0.15
    没è§ģè¿ĩ
    0.15
    空åīį
    0.14
     unprecedented
    0.14
    è§ģè¿ĩ
    0.13
    ç½ķè§ģ
    0.13
    Activations Density 0.044%

    No Known Activations