© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5724
    Prev
    Next
    INDEX
    Explanations

    free throw or free agent

    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
    丰åİļ
    -0.09
    é£İè²Į
    -0.09
    äºĽä»Ģä¹Ī
    -0.09
    åħļé£İ
    -0.09
    çĽĹ
    -0.09
    chio
    -0.09
    croft
    -0.09
    ä¹Ĵä¹ĵ
    -0.08
    åħĥå®Ŀ
    -0.08
    oria
    -0.08
    POSITIVE LOGITS
     Town
    0.09
    診
    0.08
     thrown
    0.08
    æŀī
    0.08
    -wrap
    0.08
    æİ¥è¿ij
    0.08
    åIJĮåŁİ
    0.07
    McC
    0.07
    å¾Ĵ
    0.07
    éĥ¨ä¸»ä»»
    0.07
    Activations Density 0.001%

    No Known Activations