© 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. 58748
    Prev
    Next
    INDEX
    Explanations

    words in code comments or headers

    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
    usk
    -0.10
    æĪij们ä¸Ģèµ·
    -0.10
    è¿Ļç§įæĥħåĨµ
    -0.10
    åįģåŃĹ
    -0.09
    ogg
    -0.09
    æĭīæĸ¯
    -0.09
    _contrib
    -0.09
    nost
    -0.09
    urv
    -0.08
    æłijæŀĿ
    -0.08
    POSITIVE LOGITS
     per
    0.09
    å¼ģ
    0.09
    IK
    0.09
    èĽ¤
    0.09
    ede
    0.09
    icles
    0.08
    çĹ¿
    0.08
     Impress
    0.08
    æľĪä¸Ń
    0.08
    èµ·çłģ
    0.08
    Activations Density 0.001%

    No Known Activations