© 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. 49866
    Prev
    Next
    INDEX
    Explanations

    hyphenated words ending in -ium or -ous

    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
    ä¸ĩè¾Ĩ
    -0.09
    ä¸Ģåī¯
    -0.09
    åİ»åģļ
    -0.09
    .Env
    -0.09
    usi
    -0.09
    æĭ§
    -0.09
     Dunn
    -0.08
    PLEX
    -0.08
    ä¸ĭ游
    -0.08
    entic
    -0.08
    POSITIVE LOGITS
    çĸijä¼¼
    0.09
    éģĹçķĻ
    0.09
    æݨæµĭ
    0.08
    ç»ĵæŀĦè°ĥæķ´
    0.08
     полÑı
    0.08
    è¯
    0.08
    <Field
    0.08
    éģĹåĿĢ
    0.08
    7
    0.08
    åħ¸åŀĭ
    0.08
    Activations Density 0.090%

    No Known Activations