© 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. 54319
    Prev
    Next
    INDEX
    Explanations

    continue / ongoing action

    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
    ç¼ĸåĪ¶
    -0.10
    çŃĭ
    -0.09
    èµĦ产éĩįç»Ħ
    -0.09
    vette
    -0.09
    çİ«çij°
    -0.08
    rose
    -0.08
    ä¸į足
    -0.08
    åĺ¹
    -0.08
     WI
    -0.08
    两çĤ¹
    -0.08
    POSITIVE LOGITS
    继ç»Ń
    0.22
     continued
    0.18
    ç¹¼çºĮ
    0.17
    继ç»Ńä¿ĿæĮģ
    0.16
    ä»įåľ¨
    0.15
    延ç»Ń
    0.15
     continuing
    0.15
     continues
    0.15
     continue
    0.15
    continued
    0.15
    Activations Density 0.087%

    No Known Activations