© 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. 27820
    Prev
    Next
    INDEX
    Explanations

    profile picture or image update

    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
    éħ¸
    -0.11
    idden
    -0.10
    糧
    -0.10
    çĸıéĢļ
    -0.09
    Dirty
    -0.09
    éģ¿
    -0.09
    å¯Ĩ
    -0.09
    第äºĮ个
    -0.09
    ubre
    -0.08
    ENU
    -0.08
    POSITIVE LOGITS
    çħ§çīĩ
    0.11
    pic
    0.11
     pic
    0.11
    çļĦèĦ¸
    0.10
    èĦ¸
    0.10
     face
    0.10
    çļĦçħ§çīĩ
    0.10
    åģ¶åĥı
    0.10
    éĿ¢å®¹
    0.09
     picture
    0.09
    Activations Density 0.082%

    No Known Activations