© 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. 51926
    Prev
    Next
    INDEX
    Explanations

    tai chi

    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
    ities
    -0.11
    å¼¼
    -0.10
    ly
    -0.10
    大æĪ·
    -0.10
    ä¸įå°½
    -0.10
    ãĤĨ
    -0.09
    ally
    -0.09
    ä¸įæľį
    -0.09
    è¡·
    -0.09
    no
    -0.09
    POSITIVE LOGITS
    ะ
    0.12
    失è°ĥ
    0.09
    æģ¯
    0.08
    MDB
    0.08
    å¾Ĥ
    0.08
    Exclusive
    0.08
    å°ī
    0.08
    olk
    0.08
    ORIZ
    0.08
    å©Ĩ
    0.08
    Activations Density 0.008%

    No Known Activations