© 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. 21491
    Prev
    Next
    INDEX
    Explanations

    opening parenthesis or quote

    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®Ħ
    -0.09
    æŁĺ
    -0.09
    å®ģæĦ¿
    -0.09
     Wilkinson
    -0.08
    éĥħ
    -0.08
    åĵĨ
    -0.08
     Disk
    -0.08
    é¢Ŀ
    -0.08
    0
    -0.08
    ÂŃt
    -0.08
    POSITIVE LOGITS
    åŁºæľ¬éĿ¢
    0.09
    ECH
    0.09
    baum
    0.09
    åķĨæľº
    0.08
    esk
    0.08
     thơ
    0.08
    existing
    0.08
     cảnh
    0.08
    æĦĪåĬł
    0.08
    åħ¸éĽħ
    0.08
    Activations Density 0.110%

    No Known Activations