© 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. 53230
    Prev
    Next
    INDEX
    Explanations

    Tata Steel, Thames, Hale, stown

    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
    naire
    -0.11
    sing
    -0.10
    iate
    -0.10
    =https
    -0.09
    éĩįéĩį
    -0.09
    ially
    -0.09
    æĦıåĽ¾
    -0.09
    åħļæł¡
    -0.09
     ÑĤÑĥ
    -0.08
    anders
    -0.08
    POSITIVE LOGITS
    VICES
    0.10
    åģĩæĹ¥
    0.10
    alar
    0.09
    ê¸ī
    0.08
    æ¹Ķ
    0.08
    ishi
    0.08
     ÑħозÑıйÑģÑĤв
    0.08
    بÙĪابة
    0.08
    urai
    0.08
    0.08
    Activations Density 0.001%

    No Known Activations