© 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. 2981
    Prev
    Next
    INDEX
    Explanations

    enthusiasm or strong outcomes

    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
    lient
    -0.09
     Ñģобой
    -0.09
    ,,,,
    -0.09
    holder
    -0.09
    çĦ¶æĺ¯
    -0.09
    orem
    -0.09
    ev
    -0.09
    人éĥ½
    -0.08
    ãģĹãģı
    -0.08
    ç½ijå°ıç¼ĸ
    -0.08
    POSITIVE LOGITS
    èĩ¾
    0.15
    ities
    0.12
    ivi
    0.10
    ision
    0.10
    ism
    0.10
    åħ¶ä»ĸçļĦ
    0.10
    ively
    0.09
    à¸Ķร
    0.09
    ãģªãģĬ
    0.08
    entially
    0.08
    Activations Density 0.082%

    No Known Activations