© 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. 40341
    Prev
    Next
    INDEX
    Explanations

    Abu names and locations

    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
    éĢĨ
    -0.09
    ç®Ń
    -0.08
    adt
    -0.08
    æĭ¼
    -0.08
    计è¾ĥ
    -0.08
    éĻįèIJ½
    -0.08
     Hav
    -0.08
    reuse
    -0.08
    åģļåĩº
    -0.08
    quet
    -0.08
    POSITIVE LOGITS
    æ¯Ķèµ·
    0.10
    _DD
    0.09
    趸
    0.09
     англий
    0.09
    ç»°
    0.09
    åħ¬çĽĬ
    0.09
    èĸ¤
    0.09
    uche
    0.09
    tractive
    0.09
    _CLR
    0.09
    Activations Density 0.050%

    No Known Activations