© 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. 51596
    Prev
    Next
    INDEX
    Explanations

    mathematical and critical terms

    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
    imately
    -0.19
    łí
    -0.15
    ORIZED
    -0.14
    sburgh
    -0.13
    rition
    -0.12
    ITION
    -0.12
    apsed
    -0.11
    ÙĪØ·
    -0.11
    ities
    -0.11
    ancial
    -0.11
    POSITIVE LOGITS
    er
    0.36
    i
    0.28
    o
    0.25
    à¸Ļ
    0.25
    ا
    0.25
    ãĥ³
    0.24
    ×ķ
    0.24
    en
    0.24
    an
    0.23
    zelf
    0.22
    Activations Density 3.705%

    No Known Activations