© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58839
    Prev
    Next
    INDEX
    Explanations

    common articles before nouns

    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
     мил
    -0.08
    è¿Īåĩº
    -0.08
    OMB
    -0.08
    åĢĻ
    -0.08
    ivol
    -0.08
    æģ¶æĢ§
    -0.08
    ional
    -0.08
    鬲
    -0.08
    lock
    -0.08
     probable
    -0.08
    POSITIVE LOGITS
    çŀ©
    0.09
    exter
    0.09
    SSID
    0.08
    è¦ģ说
    0.08
    ku
    0.08
    çĽ²
    0.08
    .Context
    0.08
    饵
    0.08
    å°ı康
    0.08
    çĻĸ
    0.08
    Activations Density 0.004%

    No Known Activations