© 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. 48609
    Prev
    Next
    INDEX
    Explanations

    picking up or struggling to

    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
    å§Ķç»Ħç»ĩ
    -0.11
    æĬĬæĪij
    -0.10
    家ä¼Ļ
    -0.10
    ç»ĻäºĨæĪij
    -0.10
    é£İ鼨
    -0.09
    neau
    -0.09
    çĭ¡
    -0.09
    åĨ·èĹı
    -0.09
    æĦį
    -0.09
    使æĪij
    -0.09
    POSITIVE LOGITS
    好åĥıæĺ¯
    0.12
    ä¼¼ä¹İæĺ¯
    0.12
    åĥıæĺ¯
    0.10
    çĸijä¼¼
    0.10
    ä¸Ģ群人
    0.09
    rog
    0.09
    éľ²åĩº
    0.09
     presumably
    0.09
    ä¸Ģ群
    0.09
    åľ°çIJĨ
    0.08
    Activations Density 0.131%

    No Known Activations