© 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. 17340
    Prev
    Next
    INDEX
    Explanations

    priest/priests

    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
    thic
    -0.11
    ëģĶ
    -0.11
    åī¯ä¸»å¸Ń
    -0.09
    ÑģÑı
    -0.09
    igned
    -0.09
    peg
    -0.09
    大éħĴåºĹ
    -0.09
     Watkins
    -0.09
    èĩªå¦Ĥ
    -0.09
    åķ·
    -0.09
    POSITIVE LOGITS
    esses
    0.10
    ×ķת
    0.10
    ess
    0.09
    pedia
    0.09
    è¾Ī
    0.09
    «
    0.09
    ÙĪص
    0.09
    otle
    0.09
    нÑı
    0.09
    dom
    0.09
    Activations Density 0.007%

    No Known Activations