© 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. 63736
    Prev
    Next
    INDEX
    Explanations

    abstract concepts or other languages

    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
    污
    -0.09
     TAR
    -0.09
    ä»İ容
    -0.09
    éļıå¤Ħ
    -0.09
    åIJijä¸Ĭ
    -0.09
    éľĢè¦ģçĶ¨
    -0.08
    çĨł
    -0.08
    æĽĻåħī
    -0.08
    æĢ»çļĦæĿ¥è¯´
    -0.08
    Overall
    -0.08
    POSITIVE LOGITS
    æŀģèĩ´
    0.17
    è¿Ľä¸ĢæŃ¥
    0.13
    ãģķãĤī
    0.13
    éĻIJ度
    0.12
    æŀģ端
    0.11
    å·²ç»ıè¾¾åĪ°
    0.11
    åģļå¾Ĺ
    0.11
    ç²¾çĽĬæ±Ĥç²¾
    0.11
    èµ°å¾Ĺ
    0.11
    éĢ²ä¸ĢæŃ¥
    0.11
    Activations Density 0.059%

    No Known Activations