© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26253
    Prev
    Next
    INDEX
    Explanations

    insurance and NIC

    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
    Negative Logits
    çĻ£
    -0.09
    å£ķ
    -0.09
    oser
    -0.09
    _dm
    -0.09
    åĪĨåĮº
    -0.09
    èĪĮ
    -0.09
    oso
    -0.08
    кли
    -0.08
    _goto
    -0.08
    çªij
    -0.08
    POSITIVE LOGITS
    åıĤä¿Ŀ
    0.12
    ç¼´è´¹
    0.11
    社ä¿Ŀ
    0.10
    社ä¼ļä¿ĿéĻ©
    0.10
    åħ»èĢģéĩij
    0.10
    åħ»èĢģä¿ĿéĻ©
    0.10
    umes
    0.10
    ssa
    0.10
    åħ»èĢģ
    0.09
    åĮ»çĸĹä¿ĿéĻ©
    0.09
    Activations Density 0.054%

    No Known Activations