© 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. 11262
    Prev
    Next
    INDEX
    Explanations

    positive and negative sentiments followed by context

    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
    说åĩºæĿ¥
    -0.10
    ä¿İ
    -0.10
    åĪģ
    -0.09
    åijĬè¯ī大家
    -0.09
    让人
    -0.09
    Ñĩин
    -0.09
    çĥŃçĤ¹
    -0.09
    ç»Ļ人
    -0.09
    纤
    -0.08
    Õ³
    -0.08
    POSITIVE LOGITS
    æĦŁåĪ°
    0.12
    åĽ°æĥij
    0.11
    åıĹå½±åĵį
    0.10
    åīĮ
    0.10
    æĦŁåĬ¨
    0.10
    ç½®
    0.10
    æĥĬåĸľ
    0.10
    æĦŁåħ´è¶£
    0.10
    åIJ¯åıij
    0.09
    顾
    0.09
    Activations Density 0.099%

    No Known Activations