© 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. 20344
    Prev
    Next
    INDEX
    Explanations

    Mellon, ACM, Mellencamp

    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
    ëĭ¹
    -0.09
    à¹ģà¸ģ
    -0.09
    ç§įç§į
    -0.09
    æīĢè°ĵ
    -0.08
    ÑĢажа
    -0.08
    ANTE
    -0.08
    æ·¦
    -0.08
    ä¸Ŀä¸Ŀ
    -0.08
    ãĤīãģĦ
    -0.08
    osti
    -0.08
    POSITIVE LOGITS
    bia
    0.10
    åıģ
    0.09
    uko
    0.08
    ç¼Ł
    0.08
    åĩºåĬ¨
    0.08
    -padding
    0.08
    odzi
    0.08
     Pace
    0.08
    åĩºäºĨ
    0.08
    oul
    0.08
    Activations Density 0.004%

    No Known Activations