© 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. 12383
    Prev
    Next
    INDEX
    Explanations

    consumables by New York State

    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
    éĵĻ
    -0.09
    ãĥ£
    -0.09
    ilon
    -0.08
    ç½²
    -0.08
     CERT
    -0.08
    ìķĶ
    -0.08
     Ø°
    -0.08
    uzzi
    -0.08
    leness
    -0.08
     Nass
    -0.08
    POSITIVE LOGITS
     pes
    0.09
    ведениÑı
    0.08
    iasi
    0.08
    èĩ»
    0.08
    ãģĹãģ
    0.08
    åįģäºĮäºĶ
    0.08
    yü
    0.08
    arrays
    0.08
    leÅŁ
    0.08
    大å±Ģ
    0.08
    Activations Density 0.005%

    No Known Activations