© 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. 23832
    Prev
    Next
    INDEX
    Explanations

    by nature, by definition

    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
    éĢĤå½ĵçļĦ
    -0.10
    /tiny
    -0.09
    ä»įæľª
    -0.08
    åŁº
    -0.08
    æĪij羣çļĦ
    -0.08
    èĤī
    -0.08
    ãĤĭãģ®ãģ¯
    -0.08
    ä¾Ŀæŧ
    -0.08
    èĹľ
    -0.08
    lecture
    -0.07
    POSITIVE LOGITS
    inel
    0.11
    ä¸įä¿¡
    0.11
    å¿ħçĦ¶
    0.11
    å¿ħçĦ¶ä¼ļ
    0.11
    è¿Ľåħ¥åĪ°
    0.10
    èĢĮè¨Ģ
    0.10
     necessarily
    0.10
    çĮĹ
    0.10
    å¿ħå°Ĩ
    0.10
    æĺ¯ä¸įä¼ļ
    0.09
    Activations Density 0.035%

    No Known Activations