© 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. 8044
    Prev
    Next
    INDEX
    Explanations

    programming code explanations

    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
    è¿Ļæł·è¯´
    -0.10
    è´½
    -0.10
    带ä¸Ĭ
    -0.09
     pier
    -0.09
    è¿Ļä¹Ī说
    -0.09
    çĥĻ
    -0.08
    çİ®
    -0.08
    ä¸ŃåİŁ
    -0.08
    äºĪ以
    -0.08
    æ¯Ķå¦Ĥ
    -0.08
    POSITIVE LOGITS
    å¾ĪæŃ£å¸¸
    0.09
    å·²ç»ıå¼Ģå§ĭ
    0.09
    äºĨä¸Ģéģį
    0.08
    urdy
    0.08
    itus
    0.08
    椰
    0.08
    ä»»æĢ§
    0.08
     Companion
    0.08
     Invitation
    0.08
    主è¦ģä»İäºĭ
    0.08
    Activations Density 0.134%

    No Known Activations