© 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. 50973
    Prev
    Next
    INDEX
    Explanations

    books on shelves

    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
    å¼Ĥ
    -0.11
    åĴĮæĬĢæľ¯
    -0.10
     footwear
    -0.09
    å¼±åĬ¿
    -0.09
    ç»°
    -0.09
    éģĬ
    -0.09
    ä¸ĩæĪ·
    -0.09
     Tone
    -0.09
    èĥ½åĬĽå¼º
    -0.09
    次æķ°
    -0.08
    POSITIVE LOGITS
    ç²¾è£ħ
    0.15
    shelf
    0.14
     shelf
    0.13
    书ç±į
    0.13
    ä¸Ģæľ¬
    0.13
     shelves
    0.12
    æŀ¶
    0.12
    .books
    0.11
     books
    0.11
    书åºĹ
    0.11
    Activations Density 0.082%

    No Known Activations