© 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. 49888
    Prev
    Next
    INDEX
    Explanations

    foreword and forecasts

    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
    ä½Ĩè¿Ļ
    -0.11
    nable
    -0.10
    uate
    -0.10
    ilon
    -0.10
    åħļçļĦé¢Ĩ导
    -0.09
    adero
    -0.09
    ionate
    -0.09
    丰ç¡ķ
    -0.09
    shal
    -0.09
    itional
    -0.09
    POSITIVE LOGITS
    er
    0.10
    prints
    0.10
     Fore
    0.09
    arnings
    0.09
    ä½ľä¸ļ
    0.09
    ley
    0.08
    elong
    0.08
    fore
    0.08
    i
    0.08
    åķĨæľº
    0.08
    Activations Density 0.012%

    No Known Activations