© 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. 11941
    Prev
    Next
    INDEX
    Explanations

    organizations and foundations

    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
    æļĩ
    -0.11
    rames
    -0.09
    วร
    -0.09
    ä¸į解
    -0.09
    è¶ĭåIJij
    -0.08
    è¿İæİ¥
    -0.08
    ä¸ŃåĽ½äººæ°ij
    -0.08
    apolis
    -0.08
    ot
    -0.08
    æĦŁæĤŁ
    -0.08
    POSITIVE LOGITS
    åł¤
    0.09
    æ¼ı
    0.09
    æĬĬä½ł
    0.09
    CardContent
    0.09
    æ··
    0.09
    åŃ½
    0.08
    涮
    0.08
    ourn
    0.08
    mixed
    0.08
    æĺ¯åĽ½åĨħ
    0.08
    Activations Density 0.034%

    No Known Activations