© 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. 2068
    Prev
    Next
    INDEX
    Explanations

    speaking aloud

    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
    稳妥
    -0.10
    tran
    -0.09
    Hot
    -0.08
    æł¹æľ¬
    -0.08
    hot
    -0.08
    å¤Ħ
    -0.08
    assic
    -0.08
    é¢ĺæĿIJ
    -0.08
    éķķ
    -0.08
    roe
    -0.08
    POSITIVE LOGITS
     aloud
    0.15
    大声
    0.15
    åĸĥ
    0.12
    说åĩºæĿ¥
    0.12
    spoken
    0.11
     ÑĢаÑģÑģ
    0.11
    åĶ±
    0.10
    ä½İ声
    0.10
    åļ·
    0.10
    åĴķ
    0.10
    Activations Density 0.039%

    No Known Activations