© 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. 29719
    Prev
    Next
    INDEX
    Explanations

    or its affiliates

    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
    管çIJĨåĴĮ
    -0.16
    çIJĨ解åĴĮ
    -0.14
    ä¼ģä¸ļåĴĮ
    -0.14
    ç»ıéªĮåĴĮ
    -0.14
    è´¨éĩıåĴĮ
    -0.12
     nonetheless
    -0.11
    çĶŁäº§åĴĮ
    -0.11
    æŶéĹ´åĴĮ
    -0.11
    æĸĩåĮĸåĴĮ
    -0.10
    çļĦç¼ĺæķħ
    -0.09
    POSITIVE LOGITS
    phans
    0.26
    /or
    0.24
    ifice
    0.21
    acles
    0.20
    thon
    0.19
    åħ¶å®ĥ
    0.18
    naments
    0.17
    acular
    0.16
    ignal
    0.16
    说æĺ¯
    0.16
    Activations Density 0.321%

    No Known Activations