© 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. 21534
    Prev
    Next
    INDEX
    Explanations

    lecturer

    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
    æ®Ĥ
    -0.08
    packed
    -0.08
    汶
    -0.08
    ange
    -0.08
    деÑĤ
    -0.08
    å°±æĺ¯åľ¨
    -0.08
    éĺħ读åħ¨æĸĩ
    -0.08
    æģĥ
    -0.08
    uns
    -0.08
    igor
    -0.08
    POSITIVE LOGITS
    è¯Ńæ³ķ
    0.09
    丼
    0.09
     Pty
    0.08
    鹧
    0.08
    ä¹ĥèĩ³
    0.08
    çļĦæ¨¡æł·
    0.08
    LOPT
    0.08
    éĢļä¿Ĺ
    0.08
    åī¯ä¸»ä»»
    0.08
    ToPoint
    0.08
    Activations Density 0.014%

    No Known Activations