© 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. 8248
    Prev
    Next
    INDEX
    Explanations

    garlic and ingredients

    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
    shal
    -0.10
    olis
    -0.09
    /vnd
    -0.09
    涩
    -0.09
    çĶ·çĶŁ
    -0.08
    _HAL
    -0.08
    agra
    -0.08
    Ùħبر
    -0.08
    åħ¨å¤©
    -0.08
    人çī©
    -0.08
    POSITIVE LOGITS
    åĪ¶è£ģ
    0.10
    容
    0.09
     Jae
    0.09
    éĨī
    0.09
    鸥
    0.08
     Meyer
    0.08
    çĦ¶
    0.08
    ç¿©
    0.08
    黾
    0.08
     tongues
    0.08
    Activations Density 0.012%

    No Known Activations