© 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. 21110
    Prev
    Next
    INDEX
    Explanations

    passed down or inherited

    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
    é©°
    -0.10
    ä¹ī
    -0.09
    æ³¾
    -0.09
    hack
    -0.09
    Hack
    -0.08
    義
    -0.08
    _named
    -0.08
     Param
    -0.08
    讨
    -0.08
    èĬ
    -0.08
    POSITIVE LOGITS
    继æī¿
    0.20
     inheritance
    0.19
    ä¼łæī¿
    0.19
    inherit
    0.19
    ä¸ĭä¸Ģ代
    0.18
    åŃIJåŃĻ
    0.18
    ä¼łéĢĴ
    0.18
     inherit
    0.17
     inherited
    0.17
    第ä¸ī代
    0.16
    Activations Density 0.103%

    No Known Activations