© 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. 5996
    Prev
    Next
    INDEX
    Explanations

    laser and mirrors

    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
    orton
    -0.11
    çĪ·
    -0.09
    çħ®
    -0.09
    DCF
    -0.09
    尾巴
    -0.09
    ula
    -0.08
    kul
    -0.08
    bias
    -0.08
    vin
    -0.08
    ATES
    -0.08
    POSITIVE LOGITS
    æ¿Ģåħī
    0.11
    Crud
    0.09
    .pa
    0.08
    æ±Ĭ
    0.08
    åĬłåĢį
    0.08
    çģ¼
    0.08
     laser
    0.08
    èµ°åĩºåİ»
    0.08
    èµł
    0.08
     Monter
    0.08
    Activations Density 0.168%

    No Known Activations