© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52222
    Prev
    Next
    INDEX
    Explanations

    introduction/explanation verbs

    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
    æĺ¯ä¸Ģéĥ¨
    -0.10
    è°´
    -0.10
    æĹłåĬ©
    -0.09
    æĿ¥åģļ
    -0.08
    èĥİ
    -0.08
    æļĤ
    -0.08
    æĺ¯ä¸Ģä½į
    -0.08
    æĬĬèĩªå·±
    -0.08
     Cummings
    -0.08
    ç²²
    -0.08
    POSITIVE LOGITS
    å¾Ĺ罪
    0.09
    positor
    0.09
    åĩłç§į
    0.09
    ä¸įè´Ł
    0.09
    æĻ®éģį
    0.09
    åij½é¢ĺ
    0.08
    .Disabled
    0.08
    oves
    0.08
    å¼ķèµ·äºĨ
    0.08
    OLON
    0.08
    Activations Density 0.231%

    No Known Activations