© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9335
    Prev
    Next
    INDEX
    Explanations

    with the

    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
    à¹ģà¸ģ
    -0.09
    ths
    -0.09
    è·
    -0.09
    以åıĬåħ¶ä»ĸ
    -0.09
    رش
    -0.09
    mys
    -0.09
    gow
    -0.09
    bang
    -0.09
    ä¸įèĤ¯
    -0.09
    åijĹ
    -0.08
    POSITIVE LOGITS
    éĤ£ä¹Īå¤ļ
    0.11
    è¿Ļä¹Īå¤ļ
    0.11
    å¦ĤæѤ
    0.10
     being
    0.10
    è¿Ļä¹Ī大
    0.10
    çĸ«æĥħå½±åĵį
    0.09
    åį³å°ĨåĪ°æĿ¥
    0.09
    è¿Ļä¹Ī
    0.09
    åĪ°æĿ¥
    0.09
    æľ¬äºĭ
    0.09
    Activations Density 0.047%

    No Known Activations