© 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. 55528
    Prev
    Next
    INDEX
    Explanations

    alcohol and ethanol concentrations

    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
    åĿĢ
    -0.10
    åľ¨åĽ½å¤ĸ
    -0.09
    è°İ
    -0.09
    raud
    -0.09
    åĩºåĽ½
    -0.09
     Intl
    -0.09
    çĭ±
    -0.09
    ä¿Ŀå®ļ
    -0.09
    éĵģ
    -0.09
    æĩĤå¾Ĺ
    -0.09
    POSITIVE LOGITS
    éħĴç²¾
    0.13
     alcohol
    0.11
    à¸Ńà¸ĩ
    0.11
     Alcohol
    0.11
    çĶ©
    0.10
    æī«
    0.09
    licher
    0.09
     ethanol
    0.08
    缩å°ı
    0.08
    ÐľÐĺ
    0.08
    Activations Density 0.082%

    No Known Activations