© 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. 47881
    Prev
    Next
    INDEX
    Explanations

    Timberlake & Chris Stapleton

    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
    iba
    -0.10
    踽
    -0.09
    个åĪ«
    -0.09
    ç¼ļ
    -0.09
    浪漫
    -0.09
    ifes
    -0.09
    aily
    -0.08
    éĵģ
    -0.08
    æĶ¹è¿Ľ
    -0.08
    ignet
    -0.08
    POSITIVE LOGITS
    fsp
    0.10
    ç¿Ĭ
    0.09
    ÄĽ
    0.09
    çĥĿ
    0.08
     craft
    0.08
    å°¼åħĭ
    0.08
    å°ĸåı«
    0.08
    Mad
    0.08
    ç«¥
    0.08
    ç§ijæĬĢèĤ¡ä»½
    0.08
    Activations Density 0.002%

    No Known Activations