© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20114
    Prev
    Next
    INDEX
    Explanations

    Tyler Perry, Neal Spelce

    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
    æ°Ľ
    -0.10
    à¸ĩ
    -0.09
    est
    -0.09
    éľīç´ł
    -0.09
    å±ĬæŶ
    -0.09
     Defence
    -0.08
    Ļ
    -0.08
    ness
    -0.08
    illon
    -0.08
     Crimes
    -0.08
    POSITIVE LOGITS
    åºľ
    0.11
    atology
    0.11
    à´´
    0.10
    ocities
    0.09
    iales
    0.09
    åĿİåĿ·
    0.09
    éħIJ
    0.09
    ä»Ģä¹ĪåİŁåĽł
    0.09
    æĢİä¹ĪåĽŀäºĭ
    0.09
    trans
    0.08
    Activations Density 0.006%

    No Known Activations