© 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. 38645
    Prev
    Next
    INDEX
    Explanations

    composite materials and structures

    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
    ese
    -0.10
    Ñĩен
    -0.10
    åı¤åŁİ
    -0.09
    atically
    -0.09
    èĦ±é¢ĸèĢĮåĩº
    -0.09
    绪
    -0.09
    fully
    -0.09
    æ°²
    -0.09
    _PRESENT
    -0.09
    anners
    -0.08
    POSITIVE LOGITS
    ity
    0.11
    -minded
    0.10
    iliar
    0.10
    yk
    0.09
    y
    0.09
    yı
    0.09
    ák
    0.09
    ether
    0.09
    iros
    0.08
    ï¸
    0.08
    Activations Density 0.019%

    No Known Activations