© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21444
    Prev
    Next
    INDEX
    Explanations

    how does

    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
    ç¼ī
    -0.10
    .FontStyle
    -0.10
    çľĭ好
    -0.10
    oyo
    -0.09
    _acl
    -0.09
    pageTitle
    -0.09
     themselves
    -0.09
    avis
    -0.09
    &E
    -0.09
    åIJ¹
    -0.09
    POSITIVE LOGITS
    iders
    0.09
    heets
    0.09
    ä¸įè¿ľ
    0.09
    atis
    0.08
    大夫
    0.08
    olate
    0.08
    iegel
    0.08
    éĤ£ä¸Ģ
    0.08
    åģĩæľŁ
    0.08
    orb
    0.08
    Activations Density 0.104%

    No Known Activations