© 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. 50162
    Prev
    Next
    INDEX
    Explanations

    verbs followed by continuation

    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
    ãĤ¤ãĥ³ãĤ¿ãĥ¼ãĥį
    -0.17
    ãģ¨ãģ«ãģĭ
    -0.17
    ãįī
    -0.17
    ãģĦãĤīãģ£
    -0.17
    ãĤ¢ãĤ¤ãĥĨ
    -0.17
    ãĮ¢
    -0.17
    çķ¶æĤ¨åľ¨
    -0.16
    ãĤ¢ãĥ¡ãĥª
    -0.16
    ãĥĵãĤ¸ãĥį
    -0.16
    éĽ»è©±åıĬ
    -0.16
    POSITIVE LOGITS
    åīįèĢħ
    0.08
    °
    0.06
    éģ¸
    0.06
    /trans
    0.06
    ģ
    0.06
    åIJİèĢħ
    0.05
     NON
    0.05
     DIG
    0.05
     LARGE
    0.05
     SELF
    0.05
    Activations Density 3.523%

    No Known Activations