© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7333
    Prev
    Next
    INDEX
    Explanations

    past participles indicating completion

    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
    lease
    -0.10
    åıĻè¿°
    -0.09
    ales
    -0.08
     Browse
    -0.08
    æĽĻ
    -0.08
    æ¿ĢåĬ±
    -0.08
    ceptions
    -0.08
    vic
    -0.08
    sti
    -0.08
    tutorial
    -0.08
    POSITIVE LOGITS
     conducted
    0.11
    ç½ķ
    0.11
    çļĦèĦļæŃ¥
    0.11
    åıijçİ°äºĨ
    0.11
    ç»ĵæŀľæĺ¾ç¤º
    0.11
    /testing
    0.10
    äºĨä¸Ģéģį
    0.10
    缮çļĦæĺ¯
    0.10
    ç»ĵæŀľ
    0.09
    ä¸Ģéģį
    0.09
    Activations Density 0.207%

    No Known Activations