© 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. 58275
    Prev
    Next
    INDEX
    Explanations

    taken to a destination or action

    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
    æĬ¬å¤´
    -0.11
    åīįä¸ĸ
    -0.10
    æĭ¾
    -0.10
    ÑħваÑĤ
    -0.10
    头ä¸Ĭ
    -0.10
    æºIJæºIJ
    -0.10
    èĭį
    -0.09
    äºĮ线
    -0.09
    CommandEvent
    -0.09
    èĢ³è¾¹
    -0.09
    POSITIVE LOGITS
    è¿Ľåħ¥åĪ°
    0.13
    è¿Ľåħ¥
    0.11
    èĽĭ
    0.10
    ench
    0.10
    åĽŀåĪ°
    0.10
    æĿ¥åĪ°
    0.09
    çĽ´è¾¾
    0.09
    éĢ²åħ¥
    0.09
    ç»Ļ人
    0.09
     Egg
    0.09
    Activations Density 0.095%

    No Known Activations