© 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. 27729
    Prev
    Next
    INDEX
    Explanations

    drinking vessels and beverages

    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¸į解
    -0.10
    çĦļ
    -0.10
    èĬĿ麻
    -0.09
    ä¸į平衡
    -0.09
     Sounds
    -0.09
    æĦıè§ģåıįé¦Ī
    -0.09
    leur
    -0.08
    æĺ¼å¤ľ
    -0.08
    æĿĤ
    -0.08
    gende
    -0.08
    POSITIVE LOGITS
    éħĴ
    0.12
    èij¡èIJĦéħĴ
    0.11
    æĿ¯
    0.10
    wine
    0.10
    饮çĶ¨
    0.10
    éħĴä¸ļ
    0.10
    éĨº
    0.10
    觥
    0.10
    jug
    0.09
    éĢĭ
    0.09
    Activations Density 0.049%

    No Known Activations