© 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. 10621
    Prev
    Next
    INDEX
    Explanations

    specific names followed by punctuation or titles

    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
    èĩªæķij
    -0.09
    å½ķ
    -0.09
    åĨ³è®®
    -0.09
    cie
    -0.09
     perfor
    -0.09
    çıŃåŃIJæĪIJåijĺ
    -0.09
    èĥ¤
    -0.09
    ä¸įåģļ
    -0.09
    è·Į
    -0.09
    VED
    -0.09
    POSITIVE LOGITS
    bai
    0.09
    æĭĶ
    0.09
    éļĺ
    0.08
    沫
    0.08
    çļĦæĪIJéķ¿
    0.08
     neur
    0.08
    omat
    0.08
    溯
    0.08
    atre
    0.08
    éļıå¤Ħ
    0.08
    Activations Density 0.014%

    No Known Activations