© 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. 23539
    Prev
    Next
    INDEX
    Explanations

    insurance

    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
    ../../../
    -0.13
    ÑĩаÑĤ
    -0.11
    atives
    -0.10
    åĦ¿
    -0.10
    tern
    -0.10
    YTE
    -0.09
    媳å¦ĩ
    -0.09
    ives
    -0.09
    å¦Ī
    -0.09
    çıŃ车
    -0.09
    POSITIVE LOGITS
    åħħ足
    0.09
    urge
    0.09
    anter
    0.09
    manuel
    0.08
    æľīäºĨ
    0.08
    л
    0.08
    åħħ足çļĦ
    0.08
    è¦ĨçĽĸéĿ¢
    0.08
    imed
    0.08
    enes
    0.08
    Activations Density 0.017%

    No Known Activations