© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50893
    Prev
    Next
    INDEX
    Explanations

    joining or participating

    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
    ина
    -0.10
    аÑĤÑĥÑĢ
    -0.09
    缴éĢļ车
    -0.09
    zzle
    -0.09
    åĩłä¸ªäºº
    -0.09
    夷
    -0.09
    pek
    -0.09
    kle
    -0.08
     Binder
    -0.08
    Breadcrumb
    -0.08
    POSITIVE LOGITS
    è¿Ļåľº
    0.10
    ç¼ĸç»ĩ
    0.09
    ç»ıèIJ¥èĮĥåĽ´
    0.08
    åŁºæľ¬åİŁåĪĻ
    0.08
    追
    0.08
    ä¸Ģéģĵ
    0.08
     indefinite
    0.08
    缺
    0.08
    åİŁå§ĭ
    0.08
     repost
    0.08
    Activations Density 0.022%

    No Known Activations