© 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. 4328
    Prev
    Next
    INDEX
    Explanations

    same

    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
    çķħ
    -0.09
    çļĦä¸Ģ大
    -0.08
    åħĥå®Ŀ
    -0.08
    æħİ
    -0.08
    赡
    -0.08
    çĬ¶åħĥ
    -0.08
    aved
    -0.08
    éĩįåĽŀ
    -0.08
     Affiliate
    -0.08
    شر
    -0.08
    POSITIVE LOGITS
    igs
    0.09
    bags
    0.09
    SHOT
    0.09
    ç¾İ
    0.09
    æĪª
    0.09
    æĢİä¹ĪåĽŀäºĭ
    0.09
    æıŃ
    0.09
    vice
    0.08
    对å¾ħ
    0.08
     vice
    0.08
    Activations Density 0.020%

    No Known Activations