© 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. 18232
    Prev
    Next
    INDEX
    Explanations

    writers of comic books, movies, and shows

    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
    è¯ķè¡Į
    -0.09
    æīįåıijçİ°
    -0.09
    豫
    -0.09
    APT
    -0.09
     ÑģовеÑĢÑĪ
    -0.09
    çĽ¥
    -0.09
    кан
    -0.09
    主èIJ¥
    -0.09
    å¥ĭ
    -0.08
    æĬĹè®®
    -0.08
    POSITIVE LOGITS
    iec
    0.09
    ฯ
    0.09
    oled
    0.09
    æ³Ħ
    0.09
    verb
    0.09
    vo
    0.09
    å±ı
    0.08
    unda
    0.08
     Hag
    0.08
    amped
    0.08
    Activations Density 0.027%

    No Known Activations