© 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. 38304
    Prev
    Next
    INDEX
    Explanations

    Emma person 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
    ed
    -0.10
    ending
    -0.10
     бÑĭ
    -0.09
    aldo
    -0.09
    ëĭ¤
    -0.09
    ../
    -0.09
     اÙĦدÙĬÙĨ
    -0.09
    ìĤ¬íķŃ
    -0.09
    eenth
    -0.08
    ä¹İ
    -0.08
    POSITIVE LOGITS
    ality
    0.13
    ×ķת
    0.11
    äºĭæĥħ
    0.10
    ors
    0.10
    廪
    0.10
    à¹Į
    0.10
    enance
    0.10
    å°ıäºĭ
    0.09
    ays
    0.09
    ¡
    0.09
    Activations Density 0.102%

    No Known Activations