© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38846
    Prev
    Next
    INDEX
    Explanations

    paper and paper-related items

    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
    壶
    -0.11
    éªĸ
    -0.09
    esson
    -0.09
    ä¼Ĭæĭī
    -0.09
    éĴĪ
    -0.09
    å¥Ĺ
    -0.09
    attended
    -0.08
    Ãłng
    -0.08
    _thread
    -0.08
    çłľ
    -0.08
    POSITIVE LOGITS
    纸ä¸Ĭ
    0.17
    纸
    0.11
    è½½ä½ĵ
    0.11
    ç´Ļ
    0.11
     бÑĥмаг
    0.10
     papel
    0.10
    -paper
    0.09
     paper
    0.09
    paper
    0.09
    åIJįçīĩ
    0.09
    Activations Density 0.040%

    No Known Activations