© 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. 37057
    Prev
    Next
    INDEX
    Explanations

    Dub and Dublin

    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
    æ¦Ķ
    -0.11
    èĻı
    -0.10
    Ñħод
    -0.09
    æĹ·
    -0.09
    ocos
    -0.08
    è¸Į
    -0.08
    _gem
    -0.08
    åĨį度
    -0.08
    å¤§åĽ½
    -0.08
    eldo
    -0.08
    POSITIVE LOGITS
    ../../../
    0.12
    ers
    0.11
    ious
    0.10
    就说
    0.10
    erset
    0.09
    ongs
    0.09
    ATAB
    0.08
     Bols
    0.08
    ëĭĪëĭ¤
    0.08
    nowled
    0.08
    Activations Density 0.023%

    No Known Activations