© 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. 1272
    Prev
    Next
    INDEX
    Explanations

    offensive line or guard

    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
    æī«ä¸Ģæī«
    -0.10
    çĥŃ带
    -0.09
    mast
    -0.09
    诱人
    -0.09
    hest
    -0.09
    赤
    -0.09
    jee
    -0.09
    tero
    -0.08
    åħĶ
    -0.08
    æĸĻ
    -0.08
    POSITIVE LOGITS
    è¤Ĵ
    0.09
    æįĨ
    0.09
    åºĸ
    0.09
    åĽºåĮĸ
    0.09
    åĵī
    0.09
    æ¡£
    0.09
    loc
    0.08
    .CreateInstance
    0.08
    Kn
    0.08
    两åij¨
    0.08
    Activations Density 0.054%

    No Known Activations