© 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. 35026
    Prev
    Next
    INDEX
    Explanations

    words ending in ene

    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
    çĦ¶æĺ¯
    -0.13
    ãģĹãģ¾ãģĨ
    -0.11
    matic
    -0.11
    ãģĹãģ¾ãģĦ
    -0.11
    allen
    -0.10
    lio
    -0.10
    ohana
    -0.10
    थ
    -0.10
    lor
    -0.09
    stoff
    -0.09
    POSITIVE LOGITS
    zelf
    0.09
    halb
    0.09
    ../
    0.09
    enticated
    0.09
    ene
    0.09
    à¸Ļำมา
    0.09
    ansk
    0.08
    aight
    0.08
    empt
    0.08
    çijĹ
    0.08
    Activations Density 0.041%

    No Known Activations