© 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. 50221
    Prev
    Next
    INDEX
    Explanations

    contributions to awards and research

    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
     bull
    -0.11
    èĺħ
    -0.10
    æŁ¥çľĭæĽ´å¤ļ
    -0.09
    龸çİĭ
    -0.09
    娣
    -0.09
    ole
    -0.08
    强çĥĪçļĦ
    -0.08
    éªĪ
    -0.08
    ijing
    -0.08
    åıī
    -0.08
    POSITIVE LOGITS
    è´¡çĮ®
    0.24
     contributions
    0.21
     contribution
    0.18
     Contribution
    0.18
     Contributions
    0.16
    contrib
    0.15
    Contrib
    0.13
    _contrib
    0.13
     contrib
    0.12
    åĬŁåĬ³
    0.12
    Activations Density 0.063%

    No Known Activations