© 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. 11259
    Prev
    Next
    INDEX
    Explanations

    color blind, color theories, colorado

    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
    è¡°
    -0.08
    é£İéĻ©
    -0.08
    éĽİ
    -0.08
     risks
    -0.08
    ray
    -0.08
    Č
    -0.08
    ris
    -0.08
    ä¿Ĺè¯Ŀ说
    -0.08
     dise
    -0.08
     ris
    -0.08
    POSITIVE LOGITS
    айн
    0.10
    åħľ
    0.10
    好çľĭ
    0.09
    istream
    0.09
    说æĪij
    0.09
    heid
    0.09
    глÑıд
    0.09
    esting
    0.09
    é¢ľèī²
    0.09
     Ñģли
    0.09
    Activations Density 0.011%

    No Known Activations