© 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. 6292
    Prev
    Next
    INDEX
    Explanations

    web technology or api

    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
    arp
    -0.09
     Boyd
    -0.09
    ätz
    -0.09
    é³Į
    -0.09
    à¹Ħà¸Ń
    -0.09
    AGO
    -0.09
    _hal
    -0.09
    _HAL
    -0.09
    OCI
    -0.09
    rance
    -0.09
    POSITIVE LOGITS
    éĢĢ
    0.10
    ç¼Ń
    0.09
     Pok
    0.08
    嵬
    0.08
    6
    0.08
    çļĦæĢģ度
    0.08
     Transit
    0.08
    ãģŃ
    0.08
    å·¡åĽŀ
    0.08
    4
    0.08
    Activations Density 0.047%

    No Known Activations