© 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. 51671
    Prev
    Next
    INDEX
    Explanations

    lively and energetic

    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
    reh
    -0.09
    累累
    -0.09
    mers
    -0.09
    rupt
    -0.09
    ле
    -0.09
    cess
    -0.09
    linger
    -0.09
    lagen
    -0.09
    uro
    -0.09
    aries
    -0.08
    POSITIVE LOGITS
    æ°Ķæ°Ľ
    0.11
    活泼
    0.11
    åĭĥåĭĥ
    0.11
    æī¾åĩĨ
    0.09
    NESS
    0.09
    Ĭ
    0.09
     Minds
    0.09
    ä¸ĩåĪĨ
    0.09
    fully
    0.09
    æľī趣çļĦ
    0.09
    Activations Density 0.003%

    No Known Activations