© 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. 6510
    Prev
    Next
    INDEX
    Explanations

    places ending in 'bury' or 'ity'

    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
    sWith
    -0.09
    surf
    -0.08
    Tar
    -0.08
    culo
    -0.08
    so
    -0.08
    大åħ¨
    -0.08
    »
    -0.08
    æĦį
    -0.08
    æľīä¿¡å¿ĥ
    -0.08
    iver
    -0.08
    POSITIVE LOGITS
    éĢĢ
    0.10
    alg
    0.09
    è¡·
    0.09
    à¸Ħà¸Ń
    0.09
    hab
    0.09
    çIJ¢
    0.09
    åľ°æĿ¿
    0.09
    vable
    0.08
    неÑĨ
    0.08
    conti
    0.08
    Activations Density 0.005%

    No Known Activations