© 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. 56927
    Prev
    Next
    INDEX
    Explanations

    GABAergic neurotransmission

    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
    éĺ³
    -0.10
    åĪĽæĸ°åıijå±ķ
    -0.10
    æ´®
    -0.09
    è§īæĤŁ
    -0.09
    骸
    -0.08
    éĩĩ
    -0.08
    à¸ķà¸Ńà¸Ļ
    -0.08
    resenter
    -0.08
    åŁİ
    -0.08
    æĪIJ交
    -0.08
    POSITIVE LOGITS
    å¯Ħæīĺ
    0.10
    æĥħ绪
    0.10
     ÑĥÑģп
    0.10
    çĦ¦èĻij
    0.10
    éĥ¦
    0.09
    æĦĶ
    0.09
    è¿Ŀæ³ķè¿Ŀè§Ħ
    0.09
    ä¸įå®ī
    0.09
    çļĦæĥħ绪
    0.09
    è¯ł
    0.08
    Activations Density 0.237%

    No Known Activations