© 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. 2948
    Prev
    Next
    INDEX
    Explanations

    dirt

    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
    hip
    -0.12
    缮åħī
    -0.09
    íĴĪ
    -0.09
    çľ¼è§Ĵ
    -0.09
    itive
    -0.09
    大æłij
    -0.09
    estr
    -0.09
     Äijò
    -0.09
    嵬
    -0.09
     УкÑĢа
    -0.09
    POSITIVE LOGITS
    俵
    0.10
    iness
    0.10
    ening
    0.09
    ormsg
    0.09
    ower
    0.09
    ORT
    0.09
    gems
    0.09
    ier
    0.08
    åĵĩ
    0.08
    ãģªãģı
    0.08
    Activations Density 0.010%

    No Known Activations