© 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. 52006
    Prev
    Next
    INDEX
    Explanations

    exposure to

    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
     Ñģобой
    -0.09
     gamb
    -0.09
    را
    -0.09
    berger
    -0.08
    袷
    -0.08
    å¼ĢæľĹ
    -0.08
    jej
    -0.08
    ulk
    -0.08
    å¼
    -0.08
     Eag
    -0.08
    POSITIVE LOGITS
    antu
    0.09
    SCO
    0.09
    alion
    0.08
     سبÙĬÙĦ
    0.08
    tright
    0.08
    å¿Ŀ
    0.08
    åĺ´éĩĮ
    0.08
     fg
    0.08
    å«£
    0.08
    tty
    0.08
    Activations Density 0.060%

    No Known Activations