© 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. 60921
    Prev
    Next
    INDEX
    Explanations

    credits or points

    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
    ç§ĺ
    -0.09
    обÑĢа
    -0.09
    ale
    -0.08
    ÙĬÙĪÙĨ
    -0.08
    çĶŁæ´»ä¸Ń
    -0.08
    ett
    -0.08
    æĶ¹
    -0.08
    æĿ³
    -0.08
     atl
    -0.08
    oust
    -0.08
    POSITIVE LOGITS
    åĬłåĪĨ
    0.11
     credits
    0.11
     points
    0.10
     credit
    0.10
    ä¸ĩ象
    0.10
     ÙĨÙĤاط
    0.09
    ä¿¡çĶ¨
    0.09
    賦
    0.09
    èIJ½ãģ¡
    0.09
    èµ°è¿ij
    0.09
    Activations Density 0.025%

    No Known Activations