© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26162
    Prev
    Next
    INDEX
    Explanations

    tensile strength properties

    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
    Negative Logits
    unos
    -0.11
    æĻº
    -0.09
    ä¿ĥ
    -0.08
    éķ¿çŁŃ
    -0.08
    chl
    -0.08
    æįĤ
    -0.08
     lev
    -0.08
    ấn
    -0.08
     Greenwich
    -0.08
    bios
    -0.08
    POSITIVE LOGITS
    强度
    0.15
     strength
    0.14
    èĸĦå¼±
    0.12
    æī¿åıĹ
    0.12
    åĬĽåѦ
    0.12
     Strength
    0.12
    èĦĨ
    0.12
    åĬłåĽº
    0.12
    æĬĹ
    0.12
    Strength
    0.12
    Activations Density 0.233%

    No Known Activations