© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8351
    Prev
    Next
    INDEX
    Explanations

    items in units of "each"

    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
    åŁºè°ĥ
    -0.09
    BaseContext
    -0.08
    orc
    -0.08
     bá»ģn
    -0.08
    æĥij
    -0.08
     fer
    -0.08
    pra
    -0.08
     bow
    -0.08
     peaks
    -0.08
    lid
    -0.08
    POSITIVE LOGITS
    ylon
    0.11
    æĺ¯ä¸Ģ座
    0.10
     İçin
    0.10
    ubo
    0.09
    ãĤ¼
    0.09
    åĪĨå¸ĥåľ¨
    0.09
    NESS
    0.09
    atre
    0.09
    prox
    0.09
    รà¸Ńà¸ĩ
    0.09
    Activations Density 0.022%

    No Known Activations