© 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. 882
    Prev
    Next
    INDEX
    Explanations

    so is/was/did/will

    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
    ä¹ŁæŃ£æĺ¯
    -0.10
    è¹Ĥ
    -0.10
    移
    -0.09
    maj
    -0.09
    çĬģ
    -0.08
    èĻ½çĦ¶æĺ¯
    -0.08
    æ²Ł
    -0.08
    èµī
    -0.08
    æĹ¢æľī
    -0.08
    æľīåĪ©
    -0.08
    POSITIVE LOGITS
    æ¸ļ
    0.10
    éĤ£äºĽ
    0.10
    åħ¶ä»ĸ
    0.09
     ren
    0.09
    åħ¶ä»ĸçļĦ
    0.09
    azo
    0.09
    æĪ·ç±į
    0.09
    æĸ¹æīį
    0.09
    åĪ«çļĦ
    0.09
    èī³
    0.08
    Activations Density 0.020%

    No Known Activations