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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36729
    Prev
    Next
    INDEX
    Explanations

    question or doubt

    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
    ROTO
    -0.11
    TriState
    -0.10
    ungan
    -0.10
    igner
    -0.09
    ç½ijæł¼
    -0.09
    aska
    -0.09
    尾巴
    -0.09
     tys
    -0.09
    WSC
    -0.09
    ç±
    -0.09
    POSITIVE LOGITS
    è§īå¾Ĺ
    0.12
    å°±è§īå¾Ĺ
    0.09
    æĺİæĺİ
    0.09
    éĥ½è§īå¾Ĺ
    0.09
    覺å¾Ĺ
    0.09
    ç»ıèIJ¥æ´»åĬ¨
    0.08
    æĦŁåıĹ
    0.08
    çħ¦
    0.08
    æĢ»è§īå¾Ĺ
    0.08
     Bust
    0.08
    Activations Density 0.010%

    No Known Activations