© 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. 37335
    Prev
    Next
    INDEX
    Explanations

    record label publisher

    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
    ç¥ŀ
    -0.09
    åĢĻ
    -0.09
    è¿Ķ
    -0.09
    人æŃ»äº¡
    -0.09
    .facebook
    -0.09
     urlString
    -0.09
     нед
    -0.09
    rä
    -0.08
    éķ¿å¤§
    -0.08
    icy
    -0.08
    POSITIVE LOGITS
    åĩºçīĪ社
    0.15
    åĩºçīĪ
    0.14
     publisher
    0.13
     publishers
    0.13
     Publisher
    0.11
    Publisher
    0.11
    åıijè¡Į
    0.11
    .publisher
    0.11
     publishing
    0.11
    èĢģæĿ¿
    0.11
    Activations Density 0.127%

    No Known Activations