© 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. 60959
    Prev
    Next
    INDEX
    Explanations

    import or export

    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
    atif
    -0.09
    èķ¨
    -0.09
    .Sdk
    -0.08
    产
    -0.08
    بغ
    -0.08
    hope
    -0.08
     vá»įng
    -0.08
    OptionsMenu
    -0.08
    -height
    -0.08
     ench
    -0.08
    POSITIVE LOGITS
    er
    0.10
    erer
    0.10
    /export
    0.09
    iert
    0.09
    ãģĻãĤĭãģ®ãģ¯
    0.09
    -NLS
    0.09
    ä»ĸ们éĥ½
    0.09
    [Index
    0.08
    åĵĩ
    0.08
    åľĪåŃIJ
    0.08
    Activations Density 0.100%

    No Known Activations