© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3129
    Prev
    Next
    INDEX
    Explanations

    suspects

    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
    æĤ²åī§
    -0.10
    æ·±å¤Ħ
    -0.09
    enda
    -0.09
    ä¸ĬçıŃæĹı
    -0.09
    ä¸Ģè¶Ł
    -0.09
    наÑĤ
    -0.09
    ift
    -0.09
    abic
    -0.09
    _presence
    -0.09
    xo
    -0.08
    POSITIVE LOGITS
    累累
    0.10
    ous
    0.09
    åľ¨åĨħçļĦ
    0.09
    sWith
    0.09
    æīª
    0.08
    à¸ķà¸Ļ
    0.08
    å®ļäºĨ
    0.08
    åľ¨æİ¥åıĹ
    0.08
    aje
    0.08
    olin
    0.08
    Activations Density 0.010%

    No Known Activations