© 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. 10732
    Prev
    Next
    INDEX
    Explanations

    performance counter IP protocol

    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
    è·Łè¿Ľ
    -0.10
    ullo
    -0.09
    åįļ主
    -0.09
    å¾®çĶŁçī©
    -0.09
    çºł
    -0.08
     Pending
    -0.08
    åįļæĸĩ
    -0.08
    FSIZE
    -0.08
     paddingHorizontal
    -0.08
    æīĵåĵį
    -0.08
    POSITIVE LOGITS
    ä¸ĩ象
    0.09
    yh
    0.09
    æ·ĭ
    0.09
     Diaz
    0.08
     Sax
    0.08
    æĿµ
    0.08
    .dp
    0.08
    IEW
    0.08
    å¥ī
    0.08
     Ñģог
    0.08
    Activations Density 0.097%

    No Known Activations