© 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. 31631
    Prev
    Next
    INDEX
    Explanations

    giving money to people

    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
    ä»Ģä¹Īåij¢
    -0.09
    jn
    -0.08
    .SetParent
    -0.08
     Building
    -0.08
    Building
    -0.07
     batt
    -0.07
    ãģĿãģĹãģ¦
    -0.07
    ARK
    -0.07
    æĪ¿
    -0.07
    è¿Ļ对
    -0.07
    POSITIVE LOGITS
    æīĵæĭĽåij¼
    0.11
    å·´å·´
    0.10
    å·®è·Ŀ
    0.09
    hub
    0.09
    缺åı£
    0.09
    lique
    0.08
    legg
    0.08
    æŁIJç§įç¨ĭ度
    0.08
    éĢĭ
    0.08
    Lng
    0.08
    Activations Density 0.045%

    No Known Activations