© 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. 39488
    Prev
    Next
    INDEX
    Explanations

    amputation

    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
    ä¸Ģä¼ļ
    -0.09
    泡沫
    -0.09
    (comm
    -0.09
    çģ¾
    -0.09
    grounds
    -0.09
    åħ¬è®¤çļĦ
    -0.08
     hamm
    -0.08
    åħ¬è®¤
    -0.08
    á»ĭch
    -0.08
    å¸ļ
    -0.08
    POSITIVE LOGITS
    çĸ¼
    0.10
    æİīäºĨ
    0.09
    æ»Ķ
    0.09
    é£İéĻ©ç®¡çIJĨ
    0.09
    éĶ·
    0.09
    追æ±Ĥ
    0.08
    ä¸įéĶĪ
    0.08
    zet
    0.08
    otos
    0.08
    Loss
    0.08
    Activations Density 0.061%

    No Known Activations