© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37020
    Prev
    Next
    INDEX
    Explanations

    names following certain titles

    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
     gyr
    -0.10
    å¤©åľ°
    -0.09
     unm
    -0.09
    è§ģéĿ¢
    -0.09
    工夫
    -0.08
    éĵİ
    -0.08
    alam
    -0.08
    adesh
    -0.08
    èĭŀ
    -0.08
    åĬ£
    -0.08
    POSITIVE LOGITS
    ÑĥÑĤÑĮ
    0.09
    ç͵åύ
    0.08
    åijĹ
    0.08
    çζåŃIJ
    0.08
    åģļèµ·
    0.08
    soles
    0.08
     Polly
    0.08
    åģ¥åº·æĪIJéķ¿
    0.08
    forder
    0.08
    ä¸ĢåIJį
    0.08
    Activations Density 0.533%

    No Known Activations