© 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. 9756
    Prev
    Next
    INDEX
    Explanations

    physics principles and science

    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
    æķıæĦŁ
    -0.10
    ç»Ī身
    -0.09
    ınt
    -0.09
    WXYZ
    -0.08
    ä¸Ģè¾ĪåŃIJ
    -0.08
     lifetime
    -0.08
    æĬ¤æłı
    -0.08
    åĩºåħ¥å¢ĥ
    -0.08
     purge
    -0.08
    åĩĨå¤ĩå·¥ä½ľ
    -0.08
    POSITIVE LOGITS
    åİŁçIJĨ
    0.21
    çī©çIJĨåѦ
    0.19
     physics
    0.16
     principles
    0.15
    çī©çIJĨ
    0.13
    åĬĽåѦ
    0.13
    å®ļå¾ĭ
    0.13
    éģĵçIJĨ
    0.12
     principle
    0.11
     Physics
    0.11
    Activations Density 0.151%

    No Known Activations