© 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. 4634
    Prev
    Next
    INDEX
    Explanations

    rescues and incidents

    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
     cod
    -0.08
    çħ¦
    -0.08
    æ¯ıåij¨
    -0.08
    åģļå¾Ĺ
    -0.08
    滥çĶ¨
    -0.08
     ìĺ¤íŀĪ볤
    -0.08
    æ¡£
    -0.07
    åŃķæľŁ
    -0.07
    ARCH
    -0.07
    oked
    -0.07
    POSITIVE LOGITS
    åįģéĩĮ
    0.10
    åĪĿæŃ¥
    0.09
    çİ°åľº
    0.09
    åľ¨çİ°åľº
    0.09
     poste
    0.09
    æݾ
    0.09
    è¿Ľåĩº
    0.09
     posted
    0.09
    èĶĵ延
    0.09
    æĥħ人
    0.09
    Activations Density 0.141%

    No Known Activations