© 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. 35192
    Prev
    Next
    INDEX
    Explanations

    reading aloud and storytelling

    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
    å´©
    -0.11
    åĬłéĢŁ
    -0.09
     Gio
    -0.09
     Flo
    -0.09
    åķĨçĶ¨
    -0.09
    è´Ńçī©ä¸Ńå¿ĥ
    -0.09
    SizePolicy
    -0.08
    æīĢåľ¨
    -0.08
    以ä¸ĭæĺ¯
    -0.08
    æ²»çIJĨ
    -0.08
    POSITIVE LOGITS
    æľĹ诵
    0.19
    诵
    0.18
    æľĹ
    0.13
    çIJħ
    0.13
    æĻ¨æĬ¥
    0.10
    读
    0.10
    åĴı
    0.10
    åIJŁ
    0.10
    æ¼Ķ讲
    0.10
    表æ¼Ķ
    0.10
    Activations Density 0.051%

    No Known Activations