© 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. 57379
    Prev
    Next
    INDEX
    Explanations

    function and type labels

    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
    æĮŁ
    -0.10
    IED
    -0.10
    åįıè®®
    -0.09
    é©®
    -0.09
    coma
    -0.09
    追
    -0.08
    åı£å¾Ħ
    -0.08
    æĺİæĻ°
    -0.08
    å§Ķåī¯ä¹¦è®°
    -0.08
     Copp
    -0.08
    POSITIVE LOGITS
    è§Ĩ
    0.10
    æı¿
    0.09
    åŃļ
    0.09
    åĭĥ
    0.09
    åħ¨çº¿
    0.08
    ifix
    0.08
    润æ»ijæ²¹
    0.08
    몰
    0.08
     guit
    0.08
    VML
    0.08
    Activations Density 0.305%

    No Known Activations