© 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. 26028
    Prev
    Next
    INDEX
    Explanations

    quoted strings

    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
    Negative Logits
    вали
    -0.10
    _vlog
    -0.10
    iros
    -0.09
    presso
    -0.09
    remely
    -0.09
    antar
    -0.08
     “âĢ¦
    -0.08
    plers
    -0.08
    å¿«æĬ¥
    -0.08
    éĥħ
    -0.08
    POSITIVE LOGITS
    ento
    0.09
    ç¾
    0.08
    ç§Ģ丽
    0.08
    羸
    0.08
    ç¼Ħ
    0.08
     Lâm
    0.08
    èµĵ
    0.08
    å¥ĭæĸĹ
    0.08
     Marriott
    0.08
    liced
    0.08
    Activations Density 0.314%

    No Known Activations