© 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. 16871
    Prev
    Next
    INDEX
    Explanations

    game outcomes

    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
    说æĺİ书
    -0.09
    æī¿åĬŀ
    -0.09
    unch
    -0.08
    èĩªå·±çļĦ
    -0.08
    çĨŁæĤīçļĦ
    -0.08
    就好
    -0.08
    Chip
    -0.08
    çģ«çĥ§
    -0.08
    éģµ
    -0.08
    ä¸įäºĨ
    -0.08
    POSITIVE LOGITS
    AGR
    0.09
    edom
    0.09
    rawn
    0.09
    è¿Ń
    0.09
    ç®Ĺ
    0.09
    ooks
    0.08
    æĺ¾çĦ¶
    0.08
    åįłé¢Ĩ
    0.08
    tre
    0.08
    Äħd
    0.08
    Activations Density 0.011%

    No Known Activations