© 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. 35822
    Prev
    Next
    INDEX
    Explanations

    emphasizing specifics

    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
    æ¿Ĥ
    -0.10
    éĢıéľ²
    -0.10
    _SAN
    -0.09
    çıij
    -0.08
    é©¿
    -0.08
     Zuk
    -0.08
    å¿įä¸įä½ı
    -0.08
    ãĥ¼ãĤ¿
    -0.08
    piel
    -0.08
    æĢ»èµĦ产
    -0.08
    POSITIVE LOGITS
    çī¹åĪ«æĺ¯
    0.23
    å°¤åħ¶æĺ¯
    0.21
     especially
    0.21
    å°¤åħ¶æĺ¯åľ¨
    0.20
    çī¹åĪ«æĺ¯åľ¨
    0.18
    especially
    0.18
    å°¤åħ¶
    0.16
     Especially
    0.16
    pecially
    0.14
    çī¹ãģ«
    0.14
    Activations Density 0.204%

    No Known Activations