© 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. 35116
    Prev
    Next
    INDEX
    Explanations

    ends meet or heads up

    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
    ç²
    -0.09
    ä¹ĭ乡
    -0.09
    ög
    -0.08
    ç³»ç»ŁçļĦ
    -0.08
    æ°¸æģĴ
    -0.08
     verm
    -0.08
    æ¯ı个人çļĦ
    -0.08
    èķī
    -0.08
    åīįä¸ī
    -0.08
    æīŃæĽ²
    -0.08
    POSITIVE LOGITS
     Fav
    0.10
    owe
    0.09
     Antar
    0.09
    oldt
    0.09
    æĶ¶æĶ¯
    0.09
    楮
    0.09
    /rand
    0.09
    åīĸ
    0.08
    å°½åı¯èĥ½
    0.08
    uant
    0.08
    Activations Density 0.004%

    No Known Activations