© 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. 40304
    Prev
    Next
    INDEX
    Explanations

    enough to

    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
    çľĭä»ĸ
    -0.10
    æµĵæµĵ
    -0.09
     compt
    -0.09
    å³Ļ
    -0.08
    ested
    -0.08
    ICES
    -0.08
    蹩
    -0.08
    æīĵä»Ĺ
    -0.08
    æµĵåİļ
    -0.08
    çĽ¸å¹²
    -0.08
    POSITIVE LOGITS
    ç´Ģ
    0.09
    å®Ļ
    0.09
    èĢĮä¸į
    0.09
    éĢ¢
    0.09
    nut
    0.09
    merce
    0.08
    纪
    0.08
    iat
    0.08
    åĨį
    0.08
    enburg
    0.08
    Activations Density 0.003%

    No Known Activations