© 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. 1772
    Prev
    Next
    INDEX
    Explanations

    crystal structure or population demographics

    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
    ph
    -0.09
    çħİ
    -0.09
    0
    -0.09
    st
    -0.08
    atan
    -0.08
    è°ģçŁ¥éģĵ
    -0.08
    è¿Ļä¹Īå¤ļå¹´
    -0.08
    çļĦéĤ£ç§į
    -0.08
    7
    -0.08
    9
    -0.08
    POSITIVE LOGITS
    éĵİ
    0.09
    ubes
    0.09
    avic
    0.09
    ?,?,
    0.08
    ¬ģ
    0.08
    éªŀ
    0.08
    _retry
    0.08
    .syntax
    0.08
    JNI
    0.08
    游æĪı代
    0.08
    Activations Density 1.234%

    No Known Activations