© 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. 56883
    Prev
    Next
    INDEX
    Explanations

    full copyright and license information

    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
    å¸Ń
    -0.09
    locks
    -0.09
    cow
    -0.08
    ç®ĹäºĨ
    -0.08
    mat
    -0.08
    èĩªåĬ©
    -0.08
    åİŁæľīçļĦ
    -0.08
    ä»ĸæĽ¾
    -0.08
     usu
    -0.08
     already
    -0.07
    POSITIVE LOGITS
    çļĦ人æĿ¥è¯´
    0.10
    çݩ家æĿ¥è¯´
    0.10
    ä¸įçĪ±
    0.10
     Maul
    0.10
    ItemAt
    0.09
    äºĨè§£æĽ´å¤ļ
    0.09
    ForResult
    0.09
    æĪĺ士æĿ¥è¯´
    0.09
    ายà¸Ļ
    0.09
    è¿Ļä¸ĢçĤ¹
    0.09
    Activations Density 0.054%

    No Known Activations