© 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. 17936
    Prev
    Next
    INDEX
    Explanations

    sorting by rating or recency

    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
    ocha
    -0.09
    à¸Ļาม
    -0.09
    奢ä¾Ī
    -0.09
    ç»®
    -0.09
    ãģ¾ãģķ
    -0.09
    ssue
    -0.09
    getReference
    -0.09
    icted
    -0.09
    .iso
    -0.08
    ä¸Ģ身
    -0.08
    POSITIVE LOGITS
     recent
    0.11
    æİĴåºı
    0.10
    è¿ijæľŁ
    0.09
    æľĢæĸ°
    0.09
    Popular
    0.09
    åĶ¿
    0.09
    Atom
    0.09
     Diamond
    0.09
    åĩij
    0.08
    å½ĵåīį
    0.08
    Activations Density 0.104%

    No Known Activations