© 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. 34923
    Prev
    Next
    INDEX
    Explanations

    Sky or TV

    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
    æ¸ł
    -0.11
     Kaw
    -0.10
    å¹½é»ĺ
    -0.10
    YRO
    -0.09
    _MACHINE
    -0.09
    abby
    -0.09
    æµģ泪
    -0.09
     KT
    -0.09
    á»ģn
    -0.09
    à¸Ńะ
    -0.09
    POSITIVE LOGITS
    åĻİ
    0.09
    è¿Ļå°±
    0.08
    箾
    0.08
    eing
    0.08
    æ´²
    0.08
    秣
    0.08
     Mahm
    0.08
    æľĢ好çļĦ
    0.08
    6
    0.08
     nud
    0.08
    Activations Density 0.004%

    No Known Activations