© 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. 6890
    Prev
    Next
    INDEX
    Explanations

    ain't followed by verb or adverb

    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
    å¹²èĦĨ
    -0.10
    ç½ijç»ľä¼łæĴŃ
    -0.09
    æŀķ头
    -0.09
    çļĦä¸Ģ项
    -0.09
    MESS
    -0.09
    è°İ
    -0.09
    çĪ±åIJĥ
    -0.09
    åĪ¹
    -0.09
    身边
    -0.09
    çļĦçľ¼åħī
    -0.09
    POSITIVE LOGITS
    enance
    0.10
    ed
    0.09
    iest
    0.09
    est
    0.09
    åħ«åŃĹ
    0.09
     gonna
    0.08
    horn
    0.08
    è¹ī
    0.08
    ees
    0.08
    bao
    0.08
    Activations Density 0.006%

    No Known Activations