© 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. 33442
    Prev
    Next
    INDEX
    Explanations

    legislative assembly

    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
    ened
    -0.09
    ä¸įæŃ»
    -0.08
    è¯ŀ
    -0.08
    anny
    -0.08
     Engl
    -0.08
    SEN
    -0.08
    .syntax
    -0.08
    åĪºæ¿Ģ
    -0.08
    æĹłæ¯Ķ
    -0.08
    æłijæŀĿ
    -0.08
    POSITIVE LOGITS
    ãģĦãģ¾ãģĻ
    0.10
    ignment
    0.10
    åĻ¤
    0.09
    æĸ°åŁİ
    0.09
    ende
    0.09
     laten
    0.09
     MEMBER
    0.09
    åIJĦèĩªçļĦ
    0.09
    worm
    0.08
    泪
    0.08
    Activations Density 0.021%

    No Known Activations