© 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. 33541
    Prev
    Next
    INDEX
    Explanations

    large numbers and quantities

    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
     ÑģобÑģÑĤвенно
    -0.10
    人们对
    -0.10
    ä»ĸ们çļĦ
    -0.10
    ìĶ©
    -0.09
    burger
    -0.09
    äºĽ
    -0.09
    æĥ³ä¸įåĪ°
    -0.08
    åķ¸
    -0.08
    çłĶ究æĬ¥åijĬ
    -0.08
    æĤłæĤł
    -0.08
    POSITIVE LOGITS
    ingly
    0.09
    ardy
    0.09
    ../
    0.09
    平稳
    0.09
    ponge
    0.09
    izontal
    0.09
     Miles
    0.08
    erate
    0.08
    sted
    0.08
    onde
    0.08
    Activations Density 0.072%

    No Known Activations