© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8878
    Prev
    Next
    INDEX
    Explanations

    ready to fire

    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
    交ç»Ļ
    -0.09
    åħļåĴĮ
    -0.09
     Patterson
    -0.09
    Ñģо
    -0.09
    éľĦ
    -0.09
    åĭĺ
    -0.08
    å½ķ
    -0.08
    èģĶ
    -0.08
    td
    -0.08
    寰
    -0.08
    POSITIVE LOGITS
     ready
    0.18
    ready
    0.16
     sẵn
    0.14
     READY
    0.14
    -ready
    0.13
    å¤ĩ
    0.13
    åĩĨå¤ĩ好
    0.13
    éļıæŶ
    0.12
     Ready
    0.12
    _ready
    0.12
    Activations Density 0.055%

    No Known Activations