© 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. 9816
    Prev
    Next
    INDEX
    Explanations

    land, homes, services

    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
    éĢ¼
    -0.10
    æłī
    -0.09
    é£İäºij
    -0.09
    寡
    -0.09
    æ°´åĪĨ
    -0.09
    .dds
    -0.08
    зав
    -0.08
    _bus
    -0.08
    adesh
    -0.08
    åıijè¨Ģ人
    -0.08
    POSITIVE LOGITS
    åĽ´è§Ĥ
    0.09
    æŃ£çīĪ
    0.09
    æĺĿ
    0.09
     extra
    0.09
    ä¼ĺè´¨çļĦ
    0.08
    åŁºè°ĥ
    0.08
    æĸ°çļĦ
    0.08
    avor
    0.08
    erval
    0.08
    ä¸Ģåı£æ°Ķ
    0.08
    Activations Density 0.174%

    No Known Activations