© 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. 7349
    Prev
    Next
    INDEX
    Explanations

    world, Earth

    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
    chant
    -0.10
    overe
    -0.09
    çħŀ
    -0.08
    æĬĦ
    -0.08
    å£
    -0.08
    æľŁæľ«
    -0.08
    è¿ľå¤Ħ
    -0.08
    è¯Ŀ
    -0.08
     Lara
    -0.08
    adro
    -0.08
    POSITIVE LOGITS
    ä¸ĸä¸Ĭ
    0.21
    ä¸ĸéĹ´
    0.19
    ä¸ĸ
    0.16
    人éĹ´
    0.16
    ä¸ĸçķĮä¸Ĭ
    0.14
    è¿Ļ个ä¸ĸçķĮ
    0.14
    åľ°çIJĥä¸Ĭ
    0.14
    ä¸ĸ人
    0.12
    ä¸Ģä¸ĸ
    0.12
     ìĦ¸ìĥģ
    0.11
    Activations Density 0.064%

    No Known Activations