© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40047
    Prev
    Next
    INDEX
    Explanations

    not displayed, loading, submit, firing, showing

    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
    ivr
    -0.11
    åģļçļĦäºĭ
    -0.10
    åħ±åIJĮä½ĵ
    -0.09
    æIJľç´¢å¼ķæĵİ
    -0.09
    æ¸ħæī«
    -0.08
    å°ijè§ģ
    -0.08
    åĽ½æľī
    -0.08
    èĩªè±ª
    -0.08
    åIJĦæľī
    -0.08
    åIJĦèĩª
    -0.08
    POSITIVE LOGITS
     properly
    0.12
     correctly
    0.11
     вообÑīе
    0.11
    proper
    0.11
     Proper
    0.10
    æŃ£ç¡®
    0.10
     долж
    0.10
    åºĶæľīçļĦ
    0.10
    ä¹ŁæĹłæ³ķ
    0.10
     proper
    0.10
    Activations Density 0.639%

    No Known Activations