© 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. 22926
    Prev
    Next
    INDEX
    Explanations

    times and durations

    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
    楼
    -0.10
    crate
    -0.09
    lore
    -0.09
    éľĦ
    -0.09
     reb
    -0.09
    /devices
    -0.09
    otton
    -0.09
    èĪ
    -0.09
    .NewLine
    -0.08
    æľĢ常è§ģçļĦ
    -0.08
    POSITIVE LOGITS
    ould
    0.08
    è¿Ļä¸ī个
    0.08
     dozen
    0.08
    åįĹæĸ¹
    0.07
    rib
    0.07
    沿çĿĢ
    0.07
    åĬŀ好
    0.07
     chemin
    0.07
    åĭ¤åĬ³
    0.07
    iap
    0.07
    Activations Density 0.020%

    No Known Activations