© 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. 53561
    Prev
    Next
    INDEX
    Explanations

    movement and change of state

    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
    æ¹
    -0.11
    åĩij
    -0.10
    ahi
    -0.09
    åĭĥ
    -0.09
    å°ijäºĨ
    -0.08
    åĨ
    -0.08
     msm
    -0.08
    满æĦıçļĦ
    -0.08
    æĪİ
    -0.08
     Carson
    -0.08
    POSITIVE LOGITS
    åĪ°
    0.11
     Ø¥ÙĦÙī
    0.09
    ç±³å°Ķ
    0.09
    COVER
    0.09
    ä¸ļä½Ļ
    0.09
    åĪ°çİ°åľ¨
    0.09
    转移åĪ°
    0.09
     اÙĦÙī
    0.09
    åĪ°æľĢåIJİ
    0.09
     Yönet
    0.09
    Activations Density 0.084%

    No Known Activations