© 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. 55515
    Prev
    Next
    INDEX
    Explanations

    Harry Potter

    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
    à¹ģ
    -0.10
    ä¸ĩçī©
    -0.10
    apos
    -0.09
    lined
    -0.09
    大æłij
    -0.09
    èĩ¾
    -0.09
    и
    -0.09
    wahl
    -0.09
    头èĦij
    -0.08
    esis
    -0.08
    POSITIVE LOGITS
    sson
    0.11
     Potter
    0.10
    ëģĶ
    0.10
     Consort
    0.09
    ../../../
    0.09
    à¸ģร
    0.09
    ãĤĪãģĨãģª
    0.09
    嵬
    0.09
     обеÑģп
    0.09
    pot
    0.09
    Activations Density 0.006%

    No Known Activations