© 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. 5916
    Prev
    Next
    INDEX
    Explanations

    rather than

    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
    MBED
    -0.09
    ariat
    -0.09
    eki
    -0.08
    ìĦľ
    -0.08
    ï¼ł
    -0.08
     Bez
    -0.07
    ä¼ı
    -0.07
    ä¸įä¸Ĭ
    -0.07
    pone
    -0.07
    mdb
    -0.07
    POSITIVE LOGITS
    使ä¹ĭ
    0.11
    æľīä»»ä½ķ
    0.11
    èĢĮä¸įæĺ¯
    0.11
    使æĪij
    0.09
    ronics
    0.09
    ç»´å¥ĩ
    0.09
    åı«æĪij
    0.09
    çľĭä½ł
    0.09
    ä»Ģä¹ĪåİŁåĽł
    0.09
    çľĭåĩº
    0.09
    Activations Density 0.028%

    No Known Activations