© 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. 977
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
    顶å±Ĥ设计
    -0.10
    è£ħæī®
    -0.10
    åĩºç§Ł
    -0.09
    çŁ¾
    -0.09
    åħ¬åħ±æľįåĬ¡
    -0.09
    解æĶ¾æĢĿæĥ³
    -0.09
    æĹłç§ģ
    -0.09
    é£ĺ
    -0.09
    multipart
    -0.08
    ettle
    -0.08
    POSITIVE LOGITS
    ç¥ľ
    0.09
    /lic
    0.09
    rch
    0.09
    éĤ´
    0.09
    pora
    0.08
    -exclusive
    0.08
     anv
    0.08
    inals
    0.08
     nhuáºŃn
    0.08
    /arch
    0.08
    Activations Density 0.032%

    No Known Activations