© 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. 62940
    Prev
    Next
    INDEX
    Explanations

    actions and their consequences

    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
    æīĢéľĢçļĦ
    -0.11
    æ·±æ·±åľ°
    -0.10
    Nom
    -0.10
    æīĭä¸ŃçļĦ
    -0.10
    æĭ¾
    -0.09
    åıijå±ķæĸ¹åIJij
    -0.09
    主宰
    -0.09
    çĶŁåij½çļĦ
    -0.09
    åIJįä¹ī
    -0.09
    åıijå±ķ缮æłĩ
    -0.09
    POSITIVE LOGITS
    çĶ¨æĿ¥
    0.09
    GES
    0.08
    oulos
    0.08
    èĩªçĦ¶æĺ¯
    0.08
    èģĶç³»æĪij们
    0.08
    Ļ¨
    0.08
    æľ¬äºº
    0.08
    nels
    0.08
    ноп
    0.08
    ä¸įä¿¡
    0.08
    Activations Density 0.306%

    No Known Activations