© 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. 3322
    Prev
    Next
    INDEX
    Explanations

    winery, brewery, beer, hop

    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
    è·¸
    -0.10
    ä¹ĭæīĢ
    -0.10
    ç¦Ħ
    -0.10
    çī¹æ´¾
    -0.09
    çĶŁçĹħ
    -0.09
    âĴ¸
    -0.09
    è¿IJè´¹
    -0.09
    è²Į
    -0.09
    erb
    -0.08
    çĤ·
    -0.08
    POSITIVE LOGITS
    yard
    0.09
    åľºåĿĩ
    0.09
     дело
    0.09
    æĹģ
    0.09
    è¿ľæĻ¯
    0.09
     refuse
    0.09
    hop
    0.08
    æĪ¿
    0.08
    heap
    0.08
    fol
    0.08
    Activations Density 0.067%

    No Known Activations