© 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. 56919
    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
    ä¸ļä½Ļ
    -0.10
    angu
    -0.09
    åĸĿæ°´
    -0.09
    åݨ
    -0.09
    æĦł
    -0.09
    èĩªçĦ¶ä¿ĿæĬ¤
    -0.09
    æľºæŀĦ
    -0.09
    ittal
    -0.08
    åĸĿèĮ¶
    -0.08
    åIJĥé¥Ń
    -0.08
    POSITIVE LOGITS
    æĪĪ
    0.10
    Jer
    0.09
    èħĬ
    0.09
    躬
    0.09
    oron
    0.08
     relent
    0.08
    åħ¨èĥ½
    0.08
    å°ĸ
    0.08
    ä»ij
    0.08
    urg
    0.08
    Activations Density 0.096%

    No Known Activations