© 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. 9176
    Prev
    Next
    INDEX
    Explanations

    paper and format

    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
    寡
    -0.11
    å¥
    -0.09
    ruk
    -0.09
    .hom
    -0.09
    è²Į
    -0.09
    åľ¨æ¸¸æĪıä¸Ń
    -0.09
    ç®Ĺ
    -0.08
    hsi
    -0.08
    -inline
    -0.08
    è¯ķéªĮåĮº
    -0.08
    POSITIVE LOGITS
    纸ä¸Ĭ
    0.18
    纸
    0.14
     paper
    0.13
    éĢłçº¸
    0.12
     бÑĥмаг
    0.11
    paper
    0.11
    ç´Ļ
    0.11
     parchment
    0.10
     giấy
    0.10
    楮
    0.10
    Activations Density 0.036%

    No Known Activations