© 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. 57587
    Prev
    Next
    INDEX
    Explanations

    number of / hundred years

    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
    é¢ĺ主
    -0.09
    æ·ĩ
    -0.09
    èĸ¨
    -0.09
    è·³è·ĥ
    -0.08
    éĶIJ
    -0.08
    -offs
    -0.08
    æ¨Ł
    -0.08
    å¾Ī好
    -0.08
     stiff
    -0.08
    åĪĹ
    -0.08
    POSITIVE LOGITS
    aturas
    0.10
    ä¸İåħ¶
    0.10
    iÄĩ
    0.09
    æºĥ
    0.09
    ä¿¡ãģĺ
    0.08
    çĽ¸ä¿¡
    0.08
    DSP
    0.08
    çľĭä¸įè§ģ
    0.08
    è¿ĩ大
    0.08
    缸åºĶçļĦ
    0.08
    Activations Density 0.056%

    No Known Activations