© 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. 50307
    Prev
    Next
    INDEX
    Explanations

    composite materials

    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
    èĪį
    -0.11
    dio
    -0.10
    è·³
    -0.09
    sticks
    -0.09
    åĸĺ
    -0.09
    ugen
    -0.08
    oti
    -0.08
    å¸Įå°Ķ
    -0.08
    è±ģ
    -0.08
    åĵĨ
    -0.08
    POSITIVE LOGITS
    åĬ²
    0.10
    æĸ°æĿIJæĸĻ
    0.10
    nev
    0.09
    æĿŁ
    0.09
    OPTIONS
    0.09
    .pojo
    0.09
    é¢
    0.09
     Downing
    0.09
    éļIJ身
    0.08
    ä¸Ģéģĵ
    0.08
    Activations Density 0.091%

    No Known Activations