© 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. 17399
    Prev
    Next
    INDEX
    Explanations

    box office

    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
    è¾Ł
    -0.11
    æĬ½
    -0.09
    èĸı
    -0.09
    çģ°å°ĺ
    -0.09
    æļ´éľ²
    -0.09
    æĦıåij³
    -0.09
    èĤļåŃIJ
    -0.09
    äº®çĽ¸
    -0.09
     kolej
    -0.09
    èķĹ
    -0.09
    POSITIVE LOGITS
    票æĪ¿
    0.12
    adr
    0.10
    ìĬ¤íĥĢ
    0.09
    ADR
    0.09
     Extr
    0.09
    ElementException
    0.09
    大çĽĺ
    0.09
    æĪIJé¾Ļ
    0.09
    溺
    0.08
    空çĻ½
    0.08
    Activations Density 0.065%

    No Known Activations