© 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. 1764
    Prev
    Next
    INDEX
    Explanations

    height: 6'4"

    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
    çݯç»ķ
    -0.08
    è¦ģä¹Ī
    -0.08
    YPD
    -0.08
    âľª
    -0.08
     drafts
    -0.08
    èĥ¯
    -0.08
    èĩªç§°
    -0.08
     gaz
    -0.08
    лон
    -0.08
    зав
    -0.08
    POSITIVE LOGITS
    å¼ĺæī¬
    0.10
    æ¦Ľ
    0.09
    ä¸įåħĭ
    0.09
     explan
    0.09
    onas
    0.08
    表彰
    0.08
    身é«ĺ
    0.08
    éĺµå®¹
    0.08
    çİĩ为
    0.08
    åĽŀ顾
    0.08
    Activations Density 0.054%

    No Known Activations