© 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. 8591
    Prev
    Next
    INDEX
    Explanations

    buy / purchase

    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
    å¾Ģå¤ĸ
    -0.10
    éĵ®
    -0.09
    纵横
    -0.09
    _nf
    -0.09
    lad
    -0.09
    hell
    -0.09
     PROCUREMENT
    -0.09
    åĽĬ
    -0.08
    alf
    -0.08
    edin
    -0.08
    POSITIVE LOGITS
    å¹ķ
    0.09
    éĢµ
    0.08
    ä»įæŧ
    0.08
    æѤæĸĩ
    0.08
    eref
    0.08
    èĪ¹åıª
    0.08
    å£ģ纸
    0.08
     fringe
    0.08
    æĢ§å¼º
    0.08
    kle
    0.08
    Activations Density 0.033%

    No Known Activations