© 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. 57889
    Prev
    Next
    INDEX
    Explanations

    on someone's mind

    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
    æĤ£ä¸Ĭ
    -0.09
    æĸ°ä¸ļæĢģ
    -0.09
    åł¡åŀĴ
    -0.09
    евиÑĩ
    -0.09
    è¿ĩ硬
    -0.09
    stile
    -0.09
    ä¸įèĥ½åĨį
    -0.09
    æĤ¦
    -0.08
    鸽
    -0.08
    浪漫
    -0.08
    POSITIVE LOGITS
     minds
    0.14
    å¿ĥ头
    0.13
    æĥ¦
    0.13
     thoughts
    0.13
    æĢĿ绪
    0.13
    å¿ĥæĢĿ
    0.12
     concerns
    0.11
    èIJ¦
    0.11
    忧èĻij
    0.11
    æĥ³çĿĢ
    0.11
    Activations Density 0.041%

    No Known Activations