© 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. 48709
    Prev
    Next
    INDEX
    Explanations

    would + verb

    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
    åªļ
    -0.09
    urate
    -0.08
    åij½
    -0.08
    Views
    -0.08
    rosso
    -0.08
    gart
    -0.08
    å·²ä¹ħ
    -0.08
    çħ§æł·
    -0.08
    åį´è¢«
    -0.08
    hop
    -0.08
    POSITIVE LOGITS
    çħ¤æ°Ķ
    0.11
    æĸ½
    0.09
    éħįå¥Ĺ
    0.09
    ä¸Ĭæĺł
    0.09
    转æĬĺ
    0.09
    å¥ijæľº
    0.09
    å¿«æĬ¥
    0.09
    ORB
    0.08
    otas
    0.08
    è¶Ĭ好
    0.08
    Activations Density 0.043%

    No Known Activations