© 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. 34896
    Prev
    Next
    INDEX
    Explanations

    global leader/organisation

    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
    ç¿ģ
    -0.09
     heaven
    -0.09
    åĵªæĢķæĺ¯
    -0.09
     Heaven
    -0.09
    kowski
    -0.08
    éķ¿è¿ľ
    -0.08
    ros
    -0.08
     rich
    -0.08
     National
    -0.08
    eso
    -0.08
    POSITIVE LOGITS
    ä¼ı
    0.09
    çĻ¾å¼º
    0.09
    åĵij
    0.09
    adel
    0.09
    èĦIJ
    0.08
    æĥ³æī¾
    0.08
    ToLocal
    0.08
     barg
    0.08
    è¿Ļä¹Ī大
    0.08
    çıĬçijļ
    0.08
    Activations Density 0.021%

    No Known Activations