© 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. 5902
    Prev
    Next
    INDEX
    Explanations

    detailed procedure and techniques

    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
    ileo
    -0.09
    ife
    -0.09
    ilo
    -0.08
    _XML
    -0.08
    åIJĪèµĦ
    -0.08
    nof
    -0.08
    æįĤ
    -0.08
    IFE
    -0.08
    éĥ¨åī¯
    -0.08
    å®£ä¼łæķĻèĤ²
    -0.08
    POSITIVE LOGITS
    è¯ķåīĤ
    0.12
    æ£ķèī²
    0.10
     repro
    0.10
     protocol
    0.10
    ç§ijçłĶ
    0.09
    æł·åĵģ
    0.09
    .bulk
    0.09
     pip
    0.09
    å·¥ä½ľç«Ļ
    0.09
    åѵ
    0.09
    Activations Density 0.436%

    No Known Activations