© 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. 27973
    Prev
    Next
    INDEX
    Explanations

    for many

    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
    åĺ¿
    -0.10
    æı£
    -0.09
    å¸Ń
    -0.09
    èĴĻ
    -0.09
    ElementType
    -0.09
    SELF
    -0.09
    usi
    -0.09
    gles
    -0.08
     ElementType
    -0.08
    大èĩ´
    -0.08
    POSITIVE LOGITS
    æĿ¥è¯´
    0.13
    æĿ¥è®²
    0.12
    è¿Ļä¸ĢçĤ¹
    0.11
    æĪĺ士æĿ¥è¯´
    0.11
    èĢĮè¨Ģ
    0.11
    ä¾Ĩ說
    0.11
    çݩ家æĿ¥è¯´
    0.10
    æĸĽ
    0.09
    éĤ£æł·çļĦ
    0.09
    èĥ½åģļåĪ°
    0.09
    Activations Density 0.036%

    No Known Activations