© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22311
    Prev
    Next
    INDEX
    Explanations

    senator or chairman whose

    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
    éĻĮçĶŁäºº
    -0.11
    åºĶèģĺ
    -0.10
     impres
    -0.10
     hired
    -0.09
     hiring
    -0.09
    alon
    -0.09
    æĺ¯ä¸Ģ家
    -0.09
    è¿¢
    -0.08
     trope
    -0.08
    éĽĩ
    -0.08
    POSITIVE LOGITS
    åī¯
    0.13
    æıIJæ¡Ī
    0.11
    æıIJåĩºçļĦ
    0.11
    é¢Ĩè¡Ķ
    0.11
    è®®æ¡Ī
    0.10
    踽
    0.10
    è®®åijĺ
    0.10
    æįįåį«
    0.09
    æıIJåĩºäºĨ
    0.09
    æıIJåĩº
    0.09
    Activations Density 0.087%

    No Known Activations