© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51232
    Prev
    Next
    INDEX
    Explanations

    political figures and events

    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
    ê¸Ī
    -0.09
    ä½ĵéĩį
    -0.09
    arnings
    -0.08
     Fres
    -0.08
     Pros
    -0.08
    orc
    -0.08
    åIJĦ大
    -0.08
    ATEST
    -0.08
     дол
    -0.08
    OLF
    -0.08
    POSITIVE LOGITS
    æĭ´
    0.10
    åIJĥäºı
    0.10
    çªŁ
    0.10
    æ·±åĮĸæĶ¹éĿ©
    0.09
    è½²
    0.09
    屿
    0.09
    缺åı£
    0.09
    丢失
    0.09
    延误
    0.08
    鸵
    0.08
    Activations Density 0.010%

    No Known Activations