© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18310
    Prev
    Next
    INDEX
    Explanations

    Stuart or Stuttgart names

    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
    ally
    -0.12
    sel
    -0.10
    ãģĹãģ¾ãģĦ
    -0.10
    اسب
    -0.10
    çĦ¶
    -0.09
    ãģĹãģ¾ãģĨ
    -0.09
    ening
    -0.09
    eh
    -0.09
    ogene
    -0.08
    ë¥ł
    -0.08
    POSITIVE LOGITS
    åĽŀäºĭ
    0.10
    .React
    0.09
    imir
    0.09
    ông
    0.09
    ../
    0.09
    blo
    0.09
    ãĤĪãģĨãģª
    0.09
    ision
    0.09
    ģ
    0.08
    .exec
    0.08
    Activations Density 0.004%

    No Known Activations