© 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. 21007
    Prev
    Next
    INDEX
    Explanations

    sc followed by specific suffixes

    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
    asty
    -0.10
    ector
    -0.10
     Ñģобой
    -0.10
    udev
    -0.10
     aute
    -0.09
    aina
    -0.09
    omes
    -0.08
    ieu
    -0.08
    ÙĥÙĨ
    -0.08
    gang
    -0.08
    POSITIVE LOGITS
    IENCE
    0.12
    ingly
    0.12
    orpion
    0.11
    ENARIO
    0.10
    ifique
    0.10
    HEME
    0.10
    writers
    0.10
    ç¾ļ
    0.10
    letion
    0.10
    ä¹İ
    0.10
    Activations Density 0.115%

    No Known Activations