© 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. 703
    Prev
    Next
    INDEX
    Explanations

    registered trademarks and incorporation information

    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
    Negative Logits
    éĺĻ
    -0.09
    æ³ķå¾ĭè§Ħå®ļ
    -0.09
    å¢ŀ设
    -0.08
    å¾ĭ
    -0.08
    ftware
    -0.08
    mast
    -0.08
    ortho
    -0.08
    褥
    -0.08
    éļĶ
    -0.08
    åį¯
    -0.08
    POSITIVE LOGITS
    emarks
    0.10
    anche
    0.09
    atat
    0.09
    emes
    0.09
    åĨįä¹Ł
    0.09
    çĶŁäº§åĬĽ
    0.09
    Trim
    0.09
    罨
    0.09
    INED
    0.09
    acks
    0.08
    Activations Density 0.018%

    No Known Activations