© 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. 1925
    Prev
    Next
    INDEX
    Explanations

    gas, explosion, safety, UK

    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
    èĮ«èĮ«
    -0.11
    æģį
    -0.10
    红èĮ¶
    -0.09
    ëģĮ
    -0.09
    çłĤ
    -0.09
    ç¨Ĺ
    -0.08
    engu
    -0.08
    arks
    -0.08
     ÑĥÑģили
    -0.08
    grounds
    -0.08
    POSITIVE LOGITS
    çĩĥæ°Ķ
    0.14
    天çĦ¶æ°Ķ
    0.11
     gas
    0.10
    anut
    0.09
     GAS
    0.09
    .safe
    0.09
    gas
    0.09
    çħ¤æ°Ķ
    0.09
    æ·ĭ
    0.09
     Gas
    0.08
    Activations Density 0.096%

    No Known Activations