© 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. 54863
    Prev
    Next
    INDEX
    Explanations

    first followed by a descriptor

    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
    æĪªæŃ¢
    -0.09
    arie
    -0.09
    çľ¼ä¸ĭ
    -0.09
    ä¸įå°½
    -0.09
    egin
    -0.09
    orous
    -0.09
    æĪªèĩ³
    -0.08
     оÑĩеÑĢед
    -0.08
    çĬ¯
    -0.08
    æĮĩçĤ¹
    -0.08
    POSITIVE LOGITS
    æĬ½
    0.09
    modo
    0.08
    æĪijå¿ĥéĩĮ
    0.08
    æ³ķåĪ¶
    0.08
     Palm
    0.08
    æī¿è®¤
    0.08
    æĻ°
    0.08
    eller
    0.08
     complex
    0.08
    ras
    0.08
    Activations Density 0.076%

    No Known Activations