© 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. 53271
    Prev
    Next
    INDEX
    Explanations

    vigorous activity or debate

    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
    åĬŁåĬ³
    -0.11
    éĨī
    -0.10
    ALLE
    -0.10
    ilton
    -0.10
    oria
    -0.09
    :///
    -0.09
    iw
    -0.09
    exus
    -0.09
    æ±Ģ
    -0.09
    xic
    -0.09
    POSITIVE LOGITS
    ingly
    0.11
    æ´»åĬĽ
    0.10
    èĵ¬åĭĥ
    0.10
    hart
    0.10
    ally
    0.10
    头èĦij
    0.10
    åĭĥåĭĥ
    0.09
     vigor
    0.09
    alse
    0.09
    åįģ足
    0.09
    Activations Density 0.005%

    No Known Activations