© 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. 38048
    Prev
    Next
    INDEX
    Explanations

    skin surface, neutral condition

    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
    åŁĭ
    -0.09
    ional
    -0.09
    åīįçŀ»
    -0.09
    nio
    -0.09
    åĵĢ
    -0.09
    ual
    -0.09
    设计å¸Ī
    -0.08
    èģ¿
    -0.08
    åIJĥäºĨ
    -0.08
    DEM
    -0.08
    POSITIVE LOGITS
    ä¸įéĢļ
    0.10
    æķī
    0.09
    天天
    0.09
    ãģłãģ£ãģ¦
    0.09
    æ¸ħåĩĢ
    0.09
    å¨ĩ
    0.09
     вÑĭп
    0.09
    TES
    0.09
    æīĵæī«
    0.09
    èĺħ
    0.08
    Activations Density 0.015%

    No Known Activations