© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20355
    Prev
    Next
    INDEX
    Explanations

    x-axis or x-coordinate

    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
    çĥŁçģ«
    -0.10
    èĪŀ
    -0.09
    失æķĪ
    -0.09
    ãĥĩãĥ³
    -0.08
    çĶŁåij½åĬĽ
    -0.08
    ä¸Ńæłĩ
    -0.08
    è¯ħ
    -0.08
    ieme
    -0.08
    çĸıéĢļ
    -0.08
    åŃ³
    -0.08
    POSITIVE LOGITS
    è¿Ļè¾¹
    0.10
    Photon
    0.09
    -axis
    0.09
    cts
    0.08
    utor
    0.08
    axis
    0.08
    æĬķèµĦé¡¹çĽ®
    0.08
     lẫn
    0.08
    _TOOLTIP
    0.08
    castle
    0.08
    Activations Density 0.518%

    No Known Activations