© 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. 57661
    Prev
    Next
    INDEX
    Explanations

    curb or halt

    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
    ç»ķ
    -0.09
    å½ĺ
    -0.09
    .Generated
    -0.08
    ÑıÑī
    -0.08
    ãĤ«ãĥª
    -0.08
    æħĭ
    -0.08
    æĬĺå°Ħ
    -0.08
    éĽħ
    -0.08
    apor
    -0.08
     Globe
    -0.08
    POSITIVE LOGITS
    å¾Ĺä½ı
    0.12
    ä½ı
    0.10
    ä¸ĢåĪĩ
    0.10
    ä¸įä½ı
    0.10
    åIJģ
    0.09
    iesta
    0.09
    ä½ıäºĨ
    0.09
    æ¿Ģèµ·
    0.09
    aid
    0.09
    èĩªèº«çļĦ
    0.09
    Activations Density 0.011%

    No Known Activations