© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19347
    Prev
    Next
    INDEX
    Explanations

    quantities and required amounts

    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
    кли
    -0.10
    亿ä¸ĩ
    -0.10
    æĦıè§ģåıįé¦Ī
    -0.10
    arra
    -0.09
    åįģå¹´
    -0.09
    ÙĬØ«
    -0.09
    iola
    -0.09
    --,
    -0.09
    ëĤ®
    -0.09
    éĢļåħ³
    -0.09
    POSITIVE LOGITS
    çĶ¨éĩı
    0.14
    åı¯ä¾Ľ
    0.11
    éĩı
    0.11
    é¢Ħå¤ĩ
    0.10
    ëŁī
    0.10
    ä¾ĽåºĶ
    0.09
    ä¾Ľ
    0.09
    æīĢéľĢ
    0.09
    å®ļéĩı
    0.09
    æķ°éĩı
    0.09
    Activations Density 0.036%

    No Known Activations