© 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. 37973
    Prev
    Next
    INDEX
    Explanations

    avid

    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
    ëĬ¥
    -0.10
    pping
    -0.09
    acz
    -0.08
    ters
    -0.08
    大纲
    -0.08
    å®ļäºĨ
    -0.08
    TERS
    -0.07
    æĥ¯ä¾ĭ
    -0.07
    pped
    -0.07
    اÙħÙĦ
    -0.07
    POSITIVE LOGITS
    ly
    0.12
    ä¸įå·²
    0.12
    0.11
    ión
    0.11
    åĭĥåĭĥ
    0.11
    æĹłæ¯Ķ
    0.10
     Minds
    0.10
    åĿŀ
    0.10
    alty
    0.10
    åľ°è¯´
    0.10
    Activations Density 0.004%

    No Known Activations