© 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. 49958
    Prev
    Next
    INDEX
    Explanations

    embroidery, sewing, knitting, crochet, fiber arts

    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
    éģıåĪ¶
    -0.10
    beeld
    -0.09
    ç§ijçłĶéĻ¢æīĢ
    -0.09
    æķŀ
    -0.09
    é«ĺæĺĤ
    -0.09
    éĹ®è´£
    -0.09
    æ¤įæłij
    -0.09
    htar
    -0.09
    çĽijå¯Ł
    -0.09
    å¤©çľŁ
    -0.08
    POSITIVE LOGITS
    家纺
    0.12
    纫
    0.12
    åİĤ
    0.11
    è¡£æľį
    0.11
    éĴĪç»ĩ
    0.10
    å»ł
    0.10
    纺
    0.10
    裤
    0.10
    绸
    0.10
    çªĹå¸ĺ
    0.10
    Activations Density 0.035%

    No Known Activations