© 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. 50709
    Prev
    Next
    INDEX
    Explanations

    alcohol and drinking venues

    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
    çĨ¨
    -0.10
    人å±ħ
    -0.10
    .mix
    -0.10
    çŀ½
    -0.09
    æĬĹè¡¡
    -0.09
    åijĬè¯ī她
    -0.09
    éĤ¾
    -0.09
    åĪ®
    -0.09
    粪
    -0.09
    说èĩªå·±
    -0.09
    POSITIVE LOGITS
    éħĴ
    0.20
    åĸĿéħĴ
    0.18
     beer
    0.17
    饮éħĴ
    0.16
    éħĴç²¾
    0.16
    åķ¤éħĴ
    0.16
     alcohol
    0.16
     алког
    0.14
    éħĴä¸ļ
    0.14
     Alcohol
    0.13
    Activations Density 0.155%

    No Known Activations