© 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. 17984
    Prev
    Next
    INDEX
    Explanations

    pay off, pay down, pay up

    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
    UDGE
    -0.10
    ToWorld
    -0.09
    åıįæŃ£
    -0.09
    åī¡
    -0.09
    çķĮçļĦ
    -0.09
    ÑĮÑİ
    -0.08
    аÑĩ
    -0.08
    wares
    -0.08
    acles
    -0.08
     ÐIJвÑĤоÑĢ
    -0.08
    POSITIVE LOGITS
    adic
    0.09
    æİĸ
    0.09
    tdown
    0.09
    xed
    0.09
    æĦ¿æĻ¯
    0.08
    nable
    0.08
    ably
    0.08
     insomnia
    0.08
    ter
    0.08
    ather
    0.08
    Activations Density 0.003%

    No Known Activations