© 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. 8388
    Prev
    Next
    INDEX
    Explanations

    Aleksey, Erik, Saskia, Dominik

    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
    ร
    -0.18
    ราย
    -0.18
    รà¸Ńà¸ļ
    -0.15
    รวม
    -0.15
    ระหว
    -0.13
    รา
    -0.13
    ราà¸Ħา
    -0.13
    รà¸Ń
    -0.13
    ราà¸ĩ
    -0.13
    ระ
    -0.12
    POSITIVE LOGITS
    nowledge
    0.20
    nowled
    0.18
    ernels
    0.17
    ษา
    0.15
    tober
    0.15
    NOWLED
    0.15
    ness
    0.14
    appa
    0.13
    aiser
    0.13
    ategor
    0.13
    Activations Density 0.715%

    No Known Activations