© 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. 55469
    Prev
    Next
    INDEX
    Explanations

    crochet or knitted items

    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
    å·©
    -0.09
    æ³ĵ
    -0.08
    KE
    -0.08
    延ç»Ń
    -0.08
    ÙĬØ«
    -0.08
    丰满
    -0.08
    çµ²
    -0.08
     Mann
    -0.08
    å¹ķ
    -0.08
    éĴľ
    -0.07
    POSITIVE LOGITS
    èĽŃ
    0.10
    èĹķ
    0.10
    åıĺæĢģ
    0.10
    款å¼ı
    0.10
    èĽĻ
    0.09
    ооÑĢ
    0.09
    æ°ĵ
    0.09
    åıĺå½¢
    0.09
    çĻŀ
    0.09
    åħµ
    0.08
    Activations Density 0.035%

    No Known Activations