© 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. 40170
    Prev
    Next
    INDEX
    Explanations

    do something with form

    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
     trib
    -0.10
    urai
    -0.09
    ä¿Ħ
    -0.09
    åĪĩ
    -0.09
    åīįéĢĶ
    -0.08
    conti
    -0.08
    åģ¥
    -0.08
    èĮµ
    -0.08
    壤
    -0.08
    -cont
    -0.08
    POSITIVE LOGITS
    åħ°èĬ±
    0.10
    expert
    0.10
    getApplication
    0.09
    派驻
    0.08
    Configurer
    0.08
    orne
    0.08
    HV
    0.08
    åŀĽ
    0.08
    ä¸Ĭæ¼Ķ
    0.08
     sympathetic
    0.08
    Activations Density 0.171%

    No Known Activations