© 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. 56281
    Prev
    Next
    INDEX
    Explanations

    manual lifting, factors affecting, resilience

    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
    akh
    -0.10
    lut
    -0.09
    иÑĤелÑĮ
    -0.09
    Ñħодим
    -0.09
    ÑĩиÑĤÑĭва
    -0.08
     Bruno
    -0.08
    çļĦ身份
    -0.08
    ç±į
    -0.08
    /portfolio
    -0.08
    线ä¸ĭ
    -0.08
    POSITIVE LOGITS
    以人为
    0.10
    ä¸įèĪĴæľį
    0.10
     ergonomic
    0.09
    èĪĴéĢĤçļĦ
    0.09
    æѧ
    0.09
    å¿į
    0.09
    身å¿ĥ
    0.09
    è´Łèį·
    0.09
    èĬij
    0.09
    èĮ¶åı¶
    0.09
    Activations Density 0.236%

    No Known Activations