© 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. 35729
    Prev
    Next
    INDEX
    Explanations

    "it is a"

    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®ĥæĺ¯
    -0.11
     trem
    -0.10
    æĢľ
    -0.09
    å®ĥçļĦ
    -0.09
    å®ĥ
    -0.09
    å®ĥåı¯ä»¥
    -0.09
    好çľĭçļĦ
    -0.09
    åĢļ
    -0.09
    å¯Į
    -0.09
    èļĢ
    -0.09
    POSITIVE LOGITS
    alin
    0.10
    è³ĵ
    0.10
    æĪĴ
    0.09
     Perm
    0.09
    amina
    0.08
    宾
    0.08
    arning
    0.08
    lesi
    0.08
    天èĬ±
    0.08
     пеÑĢевод
    0.08
    Activations Density 0.164%

    No Known Activations