© 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. 48061
    Prev
    Next
    INDEX
    Explanations

    statements or opinions

    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
    åĽłä¸ºæĪij们
    -0.08
    an
    -0.08
    æĬµæĬĹ
    -0.08
    åĽłä¸ºæĪij
    -0.08
     Podesta
    -0.08
    _stride
    -0.08
     McKenzie
    -0.08
    .getLocal
    -0.08
    arth
    -0.07
     squash
    -0.07
    POSITIVE LOGITS
    好æĦŁ
    0.10
    åİĨåı²æĸ°
    0.10
    对ä¸ŃåĽ½
    0.10
    对ä»ĸ
    0.10
    iveau
    0.09
    utow
    0.09
    æĤ²è§Ĥ
    0.09
    æĥ¦
    0.08
    伸åĩº
    0.08
    okers
    0.08
    Activations Density 0.032%

    No Known Activations