© 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. 12166
    Prev
    Next
    INDEX
    Explanations

    is/are constructions

    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
    yen
    -0.11
    ç¾
    -0.10
    çIJ
    -0.09
    è´±
    -0.09
    å¥ļ
    -0.08
    ÙĪÙĦÙĬ
    -0.08
    æľªæĪIJå¹´
    -0.08
    prefix
    -0.08
    æŃ¥åħ¥
    -0.08
    Suffix
    -0.08
    POSITIVE LOGITS
    éĵº
    0.10
    rette
    0.09
    æĭĽ
    0.09
    éŨæĪ·
    0.08
    runtime
    0.08
     doing
    0.08
    缬
    0.08
    raft
    0.08
    ayer
    0.08
    دة
    0.08
    Activations Density 0.021%

    No Known Activations