© 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. 33427
    Prev
    Next
    INDEX
    Explanations

    league standings and positions

    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
    åĪĿ次
    -0.11
    é¦ĸ次
    -0.10
    åı¹æģ¯
    -0.10
    åĪĿãĤģãģ¦
    -0.09
    çĵ£
    -0.09
    ä¸Ģè¾ĪåŃIJ
    -0.09
    贯穿
    -0.09
    åľ°éĿ¢
    -0.09
    Pitch
    -0.08
    å¼Ģ端
    -0.08
    POSITIVE LOGITS
    缮åīį
    0.14
     currently
    0.14
    Currently
    0.13
     Currently
    0.13
    çľ¼ä¸ĭ
    0.12
    è°Ķ
    0.11
    currently
    0.11
    缮åīįå·²ç»ı
    0.11
    çİ°åľ¨
    0.11
    æѤæŶ
    0.10
    Activations Density 0.039%

    No Known Activations