© 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. 36905
    Prev
    Next
    INDEX
    Explanations

    birds and wildlife

    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
    éĿ¢åŃĶ
    -0.10
     Morrow
    -0.09
    æĺī
    -0.09
     porr
    -0.09
    åħ´ä¸ļ
    -0.09
    CEE
    -0.09
    奴
    -0.09
    Sensor
    -0.09
    nown
    -0.09
    éĺ²æĻĴ
    -0.09
    POSITIVE LOGITS
    鸣类
    0.17
    鸣
    0.16
     birds
    0.16
     bird
    0.15
    éĩİçĶŁåĬ¨çī©
    0.14
    åĬ¨çī©
    0.13
    éĩİçĶŁ
    0.13
     wildlife
    0.12
     animal
    0.12
    å°ı鸣
    0.12
    Activations Density 0.289%

    No Known Activations