© 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. 63368
    Prev
    Next
    INDEX
    Explanations

    numbers and common words followed by punctuation

    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
     вÑħод
    -0.10
    çŀij
    -0.09
    æ¡¢
    -0.09
    楯
    -0.09
    ripper
    -0.09
    åºĩ
    -0.09
     маÑĪин
    -0.09
    civil
    -0.09
    LTR
    -0.08
    æ¯ıä¸Ģ个人
    -0.08
    POSITIVE LOGITS
    èĪĨ
    0.09
    æŃĮ
    0.09
    crast
    0.09
     Ñģоб
    0.08
    æµĬ
    0.08
    Geo
    0.08
     Со
    0.08
     Hog
    0.08
    ä¸ĢèĤ¡
    0.08
    mes
    0.08
    Activations Density 0.051%

    No Known Activations