© 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. 32135
    Prev
    Next
    INDEX
    Explanations

    areas and conditions

    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
    åĩ¡äºĭ
    -0.12
    доб
    -0.10
    roph
    -0.09
    带æĿ¥æĽ´å¤ļ
    -0.09
    éĢĻ種
    -0.09
    åħľ
    -0.09
    俾
    -0.08
    äºĶä¸Ģ
    -0.08
    å¥ĭ
    -0.08
    ä¹Ķæ²»
    -0.08
    POSITIVE LOGITS
    est
    0.09
    ollen
    0.08
    çĿĢå®ŀ
    0.08
    èĽ°
    0.08
    var
    0.08
     already
    0.08
    并ä¸į
    0.08
    ä¿ĿèįIJ
    0.08
    æĹłåħ³
    0.08
     society
    0.08
    Activations Density 0.226%

    No Known Activations