© 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. 1558
    Prev
    Next
    INDEX
    Explanations

    running backs yards

    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
    /sign
    -0.09
    ç¿İ
    -0.09
    æľºèĥ½
    -0.08
    ä¸Ń央空è°ĥ
    -0.08
    mtree
    -0.08
    åĵ¨
    -0.08
    .LA
    -0.08
    å¯Ĥå¯ŀ
    -0.08
    /Public
    -0.08
    iman
    -0.08
    POSITIVE LOGITS
    è·ijäºĨ
    0.11
    æĿ³
    0.10
    驼
    0.10
    è¸Ķ
    0.09
    esus
    0.09
    1
    0.09
    2
    0.09
    è°ĥçļ®
    0.09
    6
    0.09
    è±ļ
    0.09
    Activations Density 0.050%

    No Known Activations