© 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. 27498
    Prev
    Next
    INDEX
    Explanations

    If, because, and, even

    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
     sid
    -0.09
    rices
    -0.08
     Ernst
    -0.08
    æŁ½
    -0.08
    åĽ¢
    -0.08
    æĢĥ
    -0.08
    amage
    -0.08
    æĦŁåħ´è¶£
    -0.08
    unc
    -0.08
    åķĨä¸ļåĮĸ
    -0.08
    POSITIVE LOGITS
    avar
    0.10
    æĪijå¦Ī
    0.10
    æĪijè¦ģ
    0.10
    æĪijä¸įæĺ¯
    0.10
    æĬĬæĪij
    0.09
    åĽłä¸ºæĪij
    0.09
    åĬĽæ±Ĥ
    0.09
    DBG
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    对æĪij
    0.09
    Activations Density 0.150%

    No Known Activations