© 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. 18058
    Prev
    Next
    INDEX
    Explanations

    food items

    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
    æĪIJ为ä¸ĢåIJį
    -0.11
    è¾ħåĬ©
    -0.10
    åıĸèĥľ
    -0.10
    è¿ĻéĩĮçļĦ
    -0.09
    éĶ¦ç»£
    -0.09
    çŃīçī¹çĤ¹
    -0.09
    åĬŀäºĭ
    -0.09
    ä¾µçĬ¯
    -0.09
    çĥŁ
    -0.08
    让人
    -0.08
    POSITIVE LOGITS
    PCS
    0.10
    表éĿ¢
    0.09
    ettes
    0.09
    onis
    0.08
    人åĿĩ
    0.08
    girls
    0.08
    iere
    0.08
    eria
    0.08
    IDS
    0.08
     surface
    0.08
    Activations Density 0.058%

    No Known Activations