© 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. 52069
    Prev
    Next
    INDEX
    Explanations

    home arena, local bus, data value

    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
    åľ¨æĪijçļĦ
    -0.10
    nik
    -0.09
     поб
    -0.09
    èĦ¸
    -0.09
     psychic
    -0.09
    åĿıäºĭ
    -0.09
    _RPC
    -0.08
    rab
    -0.08
    åįļ士
    -0.08
     Emanuel
    -0.08
    POSITIVE LOGITS
     own
    0.10
    æı´
    0.10
    åĵij
    0.10
    å®ĹæŨ
    0.09
     amp
    0.09
    ç¦ıå¾·
    0.09
    æīī
    0.09
    ãģ£ãģ
    0.09
    没æľī人
    0.09
    IPA
    0.08
    Activations Density 0.252%

    No Known Activations