© 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. 21423
    Prev
    Next
    INDEX
    Explanations

    tell me what

    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
    iph
    -0.10
    ä¸į妨
    -0.10
     Paz
    -0.08
    岬
    -0.08
    .console
    -0.08
    avic
    -0.08
    禧
    -0.08
    izza
    -0.08
    зв
    -0.08
    å°º
    -0.08
    POSITIVE LOGITS
    究竣
    0.11
    ä½łçļĦ
    0.11
    ä»Ģä¹Īæĺ¯
    0.11
    æĤ¨çļĦ
    0.11
    ä»ĸçŁ¥éģĵ
    0.11
    ä»ĸ对
    0.10
    your
    0.10
    åĪ°åºķæĺ¯
    0.10
    éĿĻéĿĻ
    0.10
    究竣æĺ¯
    0.10
    Activations Density 0.011%

    No Known Activations