© 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. 21340
    Prev
    Next
    INDEX
    Explanations

    bamboo, Bam, bam, bmp

    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
    oley
    -0.10
    pike
    -0.10
    åIJŀ
    -0.09
    éĤĻ
    -0.09
    amus
    -0.09
    rade
    -0.09
    åĴĮåľ°åĮº
    -0.09
    ç¨Ĺ
    -0.08
    ate
    -0.08
    vant
    -0.08
    POSITIVE LOGITS
    æĸ°éĹ»ç½ij
    0.09
    æĭĬ
    0.09
    -haired
    0.09
    ãģĦãģĨ
    0.09
    erness
    0.09
    URAL
    0.08
    çŨ
    0.08
    mma
    0.08
    etro
    0.08
    uther
    0.08
    Activations Density 0.012%

    No Known Activations