© 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. 53544
    Prev
    Next
    INDEX
    Explanations

    suit

    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
    edException
    -0.10
    unal
    -0.10
    æīĩ
    -0.09
    .lot
    -0.09
    .chunk
    -0.09
    eil
    -0.09
    peech
    -0.09
    åĿļ硬
    -0.09
    .readString
    -0.09
    åħ¶æīĢ
    -0.09
    POSITIVE LOGITS
     suit
    0.11
    Suit
    0.10
     suite
    0.09
    æ¾Ħ
    0.09
    é¢Ĩ
    0.09
    suit
    0.09
     suits
    0.09
    4
    0.09
    åľ¨æѤä¹ĭåīį
    0.08
    æ¿ij
    0.08
    Activations Density 0.009%

    No Known Activations