© 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. 60987
    Prev
    Next
    INDEX
    Explanations

    behind the scenes

    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
    squeeze
    -0.09
    ä¸Ī
    -0.09
    éŃĤ
    -0.08
    çĨ¨
    -0.08
    åıŃ
    -0.08
    ule
    -0.08
    åĨł
    -0.08
    å¤ĸåľ°
    -0.08
    uke
    -0.08
    æīĵéĢļ
    -0.08
    POSITIVE LOGITS
    ä½ľäºĨ
    0.09
    褡
    0.09
    æīĪ
    0.09
    åģļäºĨ
    0.08
    转æĬĺ
    0.08
    iring
    0.08
    æĹłç©·
    0.08
    æīĺ
    0.08
     br
    0.08
    滩
    0.08
    Activations Density 0.006%

    No Known Activations