© 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. 52671
    Prev
    Next
    INDEX
    Explanations

    lubrication

    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
     lá»Ńa
    -0.09
    aday
    -0.09
    åįĬ导
    -0.09
    lish
    -0.09
    ignment
    -0.09
    AIM
    -0.09
    á»ijt
    -0.09
    ãģĦãģ¾ãģĻ
    -0.09
    åĪ¶æŃ¢
    -0.09
    对åħ¬åı¸
    -0.09
    POSITIVE LOGITS
    åīĤ
    0.11
    寡
    0.09
    els
    0.09
    ious
    0.09
    аÑĨион
    0.09
    绸
    0.08
    ary
    0.08
    misc
    0.08
    lessly
    0.08
    иÑĢÑĥ
    0.08
    Activations Density 0.023%

    No Known Activations