© 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. 26645
    Prev
    Next
    INDEX
    Explanations

    leadership positions and board members

    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´¬
    -0.09
    裸
    -0.09
    祼
    -0.09
    æĮŀ
    -0.08
    æĴ
    -0.08
    ÑĢаÑģÑĤ
    -0.08
     tj
    -0.08
    ounge
    -0.08
    orestation
    -0.08
    _FE
    -0.08
    POSITIVE LOGITS
    åľ¨æ¸¸æĪıä¸Ń
    0.09
    æĢĿè·¯
    0.09
    berman
    0.08
    ਬ
    0.08
     Dut
    0.08
    说è¿ĩ
    0.08
    agra
    0.08
     Fant
    0.08
    .Pod
    0.08
    ohan
    0.08
    Activations Density 0.024%

    No Known Activations