© 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. 9241
    Prev
    Next
    INDEX
    Explanations

    username or nickname

    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
     setType
    -0.09
    åĬŀ好
    -0.09
    éķĸ
    -0.09
    èŀ³
    -0.09
    lette
    -0.09
    çī¹æĸ¯
    -0.09
    untas
    -0.09
    çīºçī²
    -0.09
    çļĦ缮åħī
    -0.09
    åĵģç±»
    -0.09
    POSITIVE LOGITS
    çĶ©
    0.12
    åIJįåŃĹ
    0.09
    åIJį
    0.09
    Subsystem
    0.09
    åħīèį£
    0.09
    å¯Ĵ
    0.08
    称
    0.08
    à¸Ľà¸£à¸°à¸Īำ
    0.08
    æļ
    0.08
    .Username
    0.08
    Activations Density 0.065%

    No Known Activations