© 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. 17695
    Prev
    Next
    INDEX
    Explanations

    is / are followed by relevance or applicability

    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
    å¾Ĺä½ı
    -0.09
    diet
    -0.09
     defective
    -0.09
    åĹĶ
    -0.08
    èĩ¾
    -0.08
    æĸ°è¥¿
    -0.08
    affer
    -0.08
    èĬ³é¦Ļ
    -0.08
    otype
    -0.08
    è½
    -0.08
    POSITIVE LOGITS
    èģĨåIJ¬
    0.10
    ä¼ĹæīĢ
    0.10
    让çĶ¨æĪ·
    0.09
    ÑĤип
    0.09
     иÑģÑĤоÑĩник
    0.09
    å¥ĭåĬĽ
    0.08
    /sources
    0.08
    .conf
    0.08
    æIJŀ好
    0.08
     Witch
    0.08
    Activations Density 0.053%

    No Known Activations