© 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. 9912
    Prev
    Next
    INDEX
    Explanations

    remove file

    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
    lopen
    -0.09
    erus
    -0.09
    ests
    -0.09
    opes
    -0.09
    fts
    -0.08
    æĶ¾åģĩ
    -0.08
    å¾Īå°ı
    -0.08
    antis
    -0.08
    å±ĭ
    -0.08
    æĥ¯
    -0.08
    POSITIVE LOGITS
     khá»ıi
    0.15
    éļľç¢į
    0.10
     barriers
    0.10
    主导
    0.10
     altogether
    0.10
    å¿ĥ头
    0.10
    å¤ļä½ĻçļĦ
    0.10
    AccessType
    0.09
    è´Łæĭħ
    0.09
    妨ç¢į
    0.09
    Activations Density 0.158%

    No Known Activations