© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52906
    Prev
    Next
    INDEX
    Explanations

    leadership programs and pathways

    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
    åıijåĬ¨
    -0.10
    ç½¢
    -0.09
    åĩ¶
    -0.09
    æŀĦæĢĿ
    -0.08
    éĦ£
    -0.08
    nad
    -0.08
    社群
    -0.08
    娴
    -0.08
    Modifiers
    -0.08
    domains
    -0.08
    POSITIVE LOGITS
    说æĪij
    0.11
    ORS
    0.09
    LS
    0.09
     пÑĥÑĤ
    0.09
    elden
    0.09
     Medic
    0.09
     Pols
    0.08
     itemprop
    0.08
     Forbes
    0.08
    (CL
    0.08
    Activations Density 0.058%

    No Known Activations