© 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. 11888
    Prev
    Next
    INDEX
    Explanations

    rate following noun

    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
    bir
    -0.09
    èµı
    -0.08
    åį«è§Ĩ
    -0.08
    .Strict
    -0.08
    oca
    -0.08
    åħ¬å®īå±Ģ
    -0.08
    è³ŀ
    -0.08
    ian
    -0.08
    .Utility
    -0.08
    Ế
    -0.08
    POSITIVE LOGITS
     именно
    0.10
    å®Ĺ
    0.10
    äºİæĺ¯
    0.09
    å¾Īé«ĺçļĦ
    0.09
    åĵªæĢķ
    0.09
    oui
    0.09
    ä½łæĺ¯
    0.09
    ä¸İåıijå±ķ
    0.08
    оÑĩка
    0.08
    пÑĥ
    0.08
    Activations Density 0.050%

    No Known Activations