© 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. 19072
    Prev
    Next
    INDEX
    Explanations

    spearheading, produced, directed, front

    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
    ibil
    -0.09
    ective
    -0.09
    chia
    -0.09
    ÙĬات
    -0.08
    ampa
    -0.08
    witter
    -0.08
    à¸Ħà¸ĩ
    -0.08
    å·¡
    -0.08
    ån
    -0.08
    yth
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģåľº
    0.12
    ä¸Ģåľº
    0.11
    ä¸Ģç³»åĪĹ
    0.09
    äºĨä¸Ģç³»åĪĹ
    0.09
    ubs
    0.09
    æŀ£
    0.09
    èµĦæºIJæķ´åIJĪ
    0.09
    atar
    0.09
    çĭ¬ä¸ĢæĹłäºĮ
    0.09
    ResourceId
    0.09
    Activations Density 0.072%

    No Known Activations