© 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. 1480
    Prev
    Next
    INDEX
    Explanations

    cosmetics and scientific compounds

    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
    /mit
    -0.09
     lider
    -0.09
     cust
    -0.09
    èĢģçĪ·
    -0.09
    æĭĽåij¼
    -0.09
    oir
    -0.08
    æĹħ游æĻ¯åĮº
    -0.08
     обÑģлÑĥж
    -0.08
     tim
    -0.08
    æ²¾
    -0.08
    POSITIVE LOGITS
    被èªī
    0.10
    笼
    0.09
    Dirty
    0.09
    Unified
    0.09
    æݨçIJĨ
    0.09
    AGED
    0.09
     Execution
    0.08
    áĥĸ
    0.08
    åĮĹç¾İ
    0.08
     ÑģиÑĤ
    0.08
    Activations Density 0.172%

    No Known Activations