© 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. 63733
    Prev
    Next
    INDEX
    Explanations

    around

    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
    çİ«
    -0.09
    管çIJĨ模å¼ı
    -0.08
    kid
    -0.08
    ack
    -0.08
     PGA
    -0.08
    èķ¤
    -0.08
    iske
    -0.08
    kin
    -0.08
    dao
    -0.08
    idar
    -0.08
    POSITIVE LOGITS
    æĬī
    0.10
    è¾¹ç¼ĺ
    0.10
    æµģä¼ł
    0.09
    çļĦè¯Ŀé¢ĺ
    0.09
    åħ³éĶ®è¯į
    0.09
    çĥŁ
    0.09
    LLL
    0.09
     zwiÄħz
    0.09
    UNET
    0.09
    计éĩı
    0.09
    Activations Density 0.014%

    No Known Activations