© 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. 19377
    Prev
    Next
    INDEX
    Explanations

    Lawrence followed by a name or place

    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
    ../../../
    -0.14
    sWith
    -0.10
    åīįæīĢ
    -0.10
    åŃIJéĩĮ
    -0.10
    SSION
    -0.09
    à¸Ľà¸£à¸°à¸ª
    -0.09
    ATUS
    -0.09
    lix
    -0.09
    atur
    -0.09
    з
    -0.09
    POSITIVE LOGITS
    дол
    0.12
    fully
    0.09
    bred
    0.09
    oir
    0.09
    à¦ī
    0.09
    rim
    0.09
    nings
    0.09
     ë¶Ī구íķĺê³ł
    0.08
    burger
    0.08
    oft
    0.08
    Activations Density 0.007%

    No Known Activations