© 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. 4712
    Prev
    Next
    INDEX
    Explanations

    Norwich, Suffolk, Norfolk

    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
    åijĺ
    -0.11
    å¤Ķ
    -0.09
    çĿĢéĩį
    -0.09
    åIJij社ä¼ļ
    -0.09
    åŀŃ
    -0.09
    eki
    -0.09
    ëģĶ
    -0.09
    åįĹå±±
    -0.09
    igator
    -0.08
    èĥ½æ»¡è¶³
    -0.08
    POSITIVE LOGITS
    ìĬĪ
    0.10
    æĿ¥åĽŀ
    0.09
    uate
    0.09
     thai
    0.09
    ÙĪÙĥ
    0.09
    craft
    0.08
    çĺ¸
    0.08
    antine
    0.08
    ÑģоÑģ
    0.08
    etta
    0.08
    Activations Density 0.006%

    No Known Activations