© 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. 17873
    Prev
    Next
    INDEX
    Explanations

    FFmpeg and video processing

    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
    moid
    -0.10
    ä¸įæŃ»
    -0.09
    ä¸ĢåĪĩ
    -0.09
     اÙĦسÙĬ
    -0.08
    angan
    -0.08
     меÑĢ
    -0.08
     PID
    -0.08
     Collector
    -0.08
    éĽĨä½ĵ
    -0.08
    uby
    -0.08
    POSITIVE LOGITS
    thouse
    0.12
    åłĥ
    0.09
     producers
    0.09
     producer
    0.09
    .getProperties
    0.08
    acks
    0.08
    å±ĭéĩĮ
    0.08
    BlockSize
    0.08
    olie
    0.08
     Refugee
    0.08
    Activations Density 0.215%

    No Known Activations