© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52626
    Prev
    Next
    INDEX
    Explanations

    select, highlight, and mark items

    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
    éĺ»åĬĽ
    -0.10
    éŀħ
    -0.10
    atile
    -0.09
    æijĨ
    -0.09
    æŃ»äºĨ
    -0.09
    æł·åŃIJ
    -0.08
    ramid
    -0.08
    æĪijçŁ¥éģĵ
    -0.08
    åIJ¦è®¤
    -0.08
    ÑĨов
    -0.08
    POSITIVE LOGITS
    éĢī
    0.11
    éĢīæĭ
    0.11
    inch
    0.10
    侬
    0.09
    /exec
    0.09
    åıĸè¯ģ
    0.08
    åIJĥæĥĬ
    0.08
    วà¸Ļ
    0.08
    ä»İ严
    0.08
     chá»įn
    0.08
    Activations Density 0.100%

    No Known Activations