© 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. 54373
    Prev
    Next
    INDEX
    Explanations

    in a phrase

    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
    èĶĵ
    -0.11
    课åłĤ
    -0.10
    é¹Ĭ
    -0.10
    æį¶
    -0.09
    erk
    -0.09
    ä¸įèĥ½åĨį
    -0.09
    课åłĤæķĻåѦ
    -0.08
    ä¸įç¦ģ
    -0.08
    abor
    -0.08
    ãĥķãĥ¬
    -0.08
    POSITIVE LOGITS
    æĶ¯éĺŁ
    0.10
    æĻ´
    0.09
    天æ°Ķ
    0.09
    å°Ĭ严
    0.09
    ä¸Ģè§Ī
    0.08
    åĢ¾
    0.08
    æĻļæľŁ
    0.08
    å¤ĸæĿ¥
    0.08
    ña
    0.08
    .Expect
    0.08
    Activations Density 0.071%

    No Known Activations