© 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. 23437
    Prev
    Next
    INDEX
    Explanations

    every x time

    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
    æıIJèµ·
    -0.08
    æĢª
    -0.08
     Bowen
    -0.08
    çķĻç»Ļ
    -0.08
    æ¯ı次
    -0.08
    atar
    -0.08
    éĻĦè¿ij
    -0.07
     cáºŃn
    -0.07
    sar
    -0.07
    anta
    -0.07
    POSITIVE LOGITS
    åĩłå¹´
    0.13
    ä¸Ģ段æŶéĹ´
    0.13
    å¤ļä¹ħ
    0.11
    åįĬå¹´
    0.11
    åįĬ个
    0.10
    å¾Īä¹ħ
    0.10
    ä¸įä¹ħ
    0.10
    ä¸ĢäºĮ
    0.10
    ä»Ģä¹Īåij¢
    0.10
    çĹ¼
    0.10
    Activations Density 0.042%

    No Known Activations