© 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. 55908
    Prev
    Next
    INDEX
    Explanations

    per unit of quantity

    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
    æĺ¼
    -0.09
     rhyme
    -0.08
    éļĶ
    -0.08
    涧
    -0.08
    è·Ŀ
    -0.08
    abbr
    -0.08
     Dest
    -0.08
    amura
    -0.08
     USDA
    -0.08
    æĺĶ
    -0.08
    POSITIVE LOGITS
    è¶ħè¶Ĭ
    0.11
    åij³éģĵ
    0.10
     capita
    0.10
    ä¸ĢåĪĨ
    0.10
    å¼ĢæĿ¥
    0.09
    иÑĩно
    0.09
    åıĮèħ¿
    0.09
    IGO
    0.09
    ition
    0.09
    cro
    0.09
    Activations Density 0.033%

    No Known Activations