© 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. 49494
    Prev
    Next
    INDEX
    Explanations

    outscored opponents by

    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
    èļĤ
    -0.10
    çļĦ人çĶŁ
    -0.09
    åĵģ
    -0.09
    åĨ·åĨ·
    -0.09
    adt
    -0.08
    çļĦ好å¤Ħ
    -0.08
    ä¸įç»ı
    -0.08
    ç«Ļéķ¿
    -0.08
    oger
    -0.08
    ä¸Ģä¸Ģ
    -0.08
    POSITIVE LOGITS
    é£İæł¼
    0.11
    éĺ²çº¿
    0.10
    Against
    0.10
    eway
    0.09
    éĺ´éģĵ
    0.09
     offense
    0.09
    вин
    0.09
     adına
    0.09
    第ä¸ĢæŃ¥
    0.09
    _STYLE
    0.09
    Activations Density 0.068%

    No Known Activations