© 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. 48198
    Prev
    Next
    INDEX
    Explanations

    began, started, launched, opened, founded

    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
    踵
    -0.09
    abant
    -0.09
    resse
    -0.09
    ä¾ĿçĦ¶æĺ¯
    -0.09
    å¹³å®ī
    -0.08
    è¿ĺä¸įå¤Ł
    -0.08
    ä»įæŧ
    -0.08
    ä¹Łèĥ½
    -0.08
    åħ¬äº¤
    -0.08
     STILL
    -0.08
    POSITIVE LOGITS
    åݻ年
    0.12
    å¼Ģå§ĭ
    0.12
    æľĢæĹ©
    0.11
    轫
    0.11
    å¹´å¼Ģå§ĭ
    0.10
    åĩłå¹´åīį
    0.10
     recently
    0.10
    æĪIJç«ĭäºİ
    0.10
    æľĢåĪĿ
    0.10
    å§ĭäºİ
    0.10
    Activations Density 0.412%

    No Known Activations