© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5695
    Prev
    Next
    INDEX
    Explanations

    skip phrases

    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
    åijĨ
    -0.11
    æĹłæĦı
    -0.10
    petition
    -0.10
    ä¸įæĺİçĻ½
    -0.10
    <quote
    -0.10
    æīįçŁ¥éģĵ
    -0.09
    ä¸įåºĶ该
    -0.09
    ä¸įç»ıæĦı
    -0.09
    ãĤį
    -0.09
    éĻĶ
    -0.09
    POSITIVE LOGITS
     preamble
    0.09
    GetCurrent
    0.09
    ä¸Ńä»ĭ
    0.09
     Skip
    0.09
    æŀ
    0.08
    Prot
    0.08
    è£Ķ
    0.08
    æ¡ij
    0.08
    erner
    0.08
    çķ´
    0.08
    Activations Density 0.021%

    No Known Activations