© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37304
    Prev
    Next
    INDEX
    Explanations

    class of [year]

    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
    å¢ĥ
    -0.10
    æĹ¥è¶ĭ
    -0.09
    æīĭæĦŁ
    -0.09
    亲åŃIJ
    -0.09
    çĪ¶åŃIJ
    -0.09
    è¦ģç´§
    -0.09
    åĽ¢å§Ķ
    -0.08
     ТÑĥÑĢ
    -0.08
    æ¶ķ
    -0.08
    æ³±
    -0.08
    POSITIVE LOGITS
    第äºĮæī¹
    0.13
    第ä¸Ģæī¹
    0.12
    è¿Ļæī¹
    0.12
    æ¯ķä¸ļ
    0.11
     cohort
    0.11
    ä¸Ģæī¹
    0.11
    çļĦä¸Ģåijĺ
    0.10
     batch
    0.10
    çıŃ
    0.10
    é¦ĸå±Ĭ
    0.10
    Activations Density 0.086%

    No Known Activations