© 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. 60615
    Prev
    Next
    INDEX
    Explanations

    creating an instance of

    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
     Elliott
    -0.09
    èĥİ
    -0.09
    MDB
    -0.08
    çªģåĩº
    -0.08
    èŁĴ
    -0.08
     Elliot
    -0.08
    追
    -0.08
    vore
    -0.08
    iest
    -0.08
     gang
    -0.08
    POSITIVE LOGITS
     instance
    0.13
    对象
    0.13
    .instances
    0.12
    _instance
    0.12
    å®ŀä¾ĭ
    0.12
     newInstance
    0.12
    $instance
    0.12
    .newInstance
    0.12
    Instances
    0.12
    instances
    0.12
    Activations Density 1.432%

    No Known Activations