© 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. 49044
    Prev
    Next
    INDEX
    Explanations

    Air Force, military, space

    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
    å±ħ
    -0.10
    oker
    -0.09
     Innoc
    -0.09
    ÑģÑĤоÑı
    -0.09
    okers
    -0.09
    âĤ¹
    -0.08
    çģ«èĬ±
    -0.08
    港åı£
    -0.08
    çĨ¨
    -0.08
    ymax
    -0.08
    POSITIVE LOGITS
    å¾Ĵ
    0.10
    æĶ¿åºľéĥ¨éŨ
    0.10
    ç«Ł
    0.10
    åĪĨ辨
    0.09
    çĤĶ
    0.09
    çĿ
    0.09
    è·Łä¸įä¸Ĭ
    0.09
    çIJī
    0.08
    设æĥ³
    0.08
    è·Łè¸ª
    0.08
    Activations Density 0.058%

    No Known Activations