© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35671
    Prev
    Next
    INDEX
    Explanations

    drunken driving alcohol intoxication

    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
    éĿĻçĶµ
    -0.10
     ank
    -0.09
    Reporter
    -0.09
    æŀ¯çĩ¥
    -0.09
    æĪIJå°±æĦŁ
    -0.09
    compression
    -0.09
    étude
    -0.08
    å¤Ħåľ¨
    -0.08
    ä¸įåIJĥ
    -0.08
    duction
    -0.08
    POSITIVE LOGITS
    éĨī
    0.23
     drunken
    0.16
    éħĴ
    0.15
    éħ©
    0.15
     drunk
    0.15
    éħĴç²¾
    0.14
    饮éħĴ
    0.14
     alcohol
    0.14
    éĨº
    0.13
     intoxicated
    0.13
    Activations Density 0.217%

    No Known Activations