© 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. 51051
    Prev
    Next
    INDEX
    Explanations

    particulate matter and soil

    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
    ICC
    -0.09
    ISM
    -0.09
    anic
    -0.09
    水管
    -0.09
    oa
    -0.08
     Microwave
    -0.08
    ãĥĪãĤ¤ãĥ¬
    -0.08
    çݯä¿Ŀ
    -0.08
     microwave
    -0.07
    çģ«çĤ¬
    -0.07
    POSITIVE LOGITS
    åħľ
    0.11
    trak
    0.10
    æĢ»éĺŁ
    0.10
    广åijĬæľįåĬ¡
    0.10
    çľ¼è§Ĵ
    0.10
    rias
    0.10
    >Password
    0.10
    erville
    0.09
    á»Ļi
    0.09
    (EXPR
    0.09
    Activations Density 0.093%

    No Known Activations