© 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. 48744
    Prev
    Next
    INDEX
    Explanations

    if you

    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
    пÑĢоиз
    -0.09
    计è¾ĥ
    -0.09
    avan
    -0.09
     ведÑĮ
    -0.09
    ania
    -0.09
    æİ¥åĬĽ
    -0.09
    åİŁå§ĭ
    -0.08
    æĪijåı¯ä»¥
    -0.08
    ä¸įä»ħæĺ¯
    -0.08
    oon
    -0.08
    POSITIVE LOGITS
    çĸ¾
    0.11
    åIJİèĢħ
    0.10
    odus
    0.10
    æľīä»»ä½ķ
    0.10
    ä½łè§īå¾Ĺ
    0.10
    KeySpec
    0.09
    æľīæĦı
    0.09
    éĺĭ
    0.09
    å¿ĥä¸Ń
    0.09
    馥
    0.09
    Activations Density 0.028%

    No Known Activations