© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    expressing thought or opinion

    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
     peter
    -0.08
     Larson
    -0.08
    亲
    -0.08
    ä¸įä½Ĩ
    -0.08
    æģ°
    -0.07
     securities
    -0.07
     UIG
    -0.07
    ç«ŁçĦ¶
    -0.07
    imer
    -0.07
     mar
    -0.07
    POSITIVE LOGITS
    å±ĬæŶ
    0.15
    è¿Ļä¹Łæĺ¯
    0.15
    åĪ°æŶåĢĻ
    0.14
    楽ãģĹãģ¿
    0.13
    æķ¬è¯·
    0.11
    ä¹Łæľĥ
    0.11
    äºīåıĸ
    0.11
     Already
    0.11
    è¿Ļæł·åģļ
    0.11
    åīįæıIJæĺ¯
    0.10
    Activations Density 0.108%

    No Known Activations