© 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. 49722
    Prev
    Next
    INDEX
    Explanations

    mathematical calculation prompts

    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
    addock
    -0.10
    ä»ħ代表
    -0.10
    å½ĵä¹ĭ
    -0.09
    ä¼Łå¤§
    -0.09
    æĦŁæħ¨
    -0.08
    talk
    -0.08
    abbr
    -0.08
    istor
    -0.08
    æ¦Ń
    -0.08
    TL
    -0.08
    POSITIVE LOGITS
    æĪIJåĵģ
    0.10
    åķ¬
    0.09
    éľĸ
    0.09
    为ä»Ģä¹Īä¸į
    0.09
    .setColumns
    0.09
    为ä»Ģä¹Īè¦ģ
    0.09
    æİ©
    0.08
     giãn
    0.08
     vad
    0.08
    客æĪ·æıIJä¾Ľ
    0.08
    Activations Density 0.044%

    No Known Activations