© 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. 20706
    Prev
    Next
    INDEX
    Explanations

    time remaining or left

    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
    åħ¬çĦ¶
    -0.12
    çĮĿ
    -0.10
    æĻ¾
    -0.09
    ÑĢам
    -0.09
    полнение
    -0.08
    atori
    -0.08
    .openapi
    -0.08
    หมà¸Ķ
    -0.08
    æĪĸå¤ļ
    -0.08
    ypad
    -0.08
    POSITIVE LOGITS
     baggage
    0.10
    çĶŃ
    0.08
     Bott
    0.08
     Ging
    0.08
    _BUF
    0.08
    REMOTE
    0.08
    åĩ¤
    0.08
    itest
    0.08
    éĽģ
    0.08
    åĨĪ
    0.08
    Activations Density 0.001%

    No Known Activations