© 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. 11593
    Prev
    Next
    INDEX
    Explanations

    age and seniority titles

    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
    龸éģĵ
    -0.08
    çİ
    -0.08
    amment
    -0.08
    acco
    -0.08
    akk
    -0.08
    nable
    -0.08
    é©¿
    -0.08
     ers
    -0.08
    åĸĿ
    -0.08
    ŀ
    -0.07
    POSITIVE LOGITS
    桧
    0.11
    æ¸
    0.10
    è¾Ī
    0.10
    ги
    0.09
    æµij
    0.09
    æĶ¿æ³ķ
    0.09
    iel
    0.09
    ubar
    0.09
    å¹´é¾Ħ段
    0.09
    lings
    0.08
    Activations Density 0.072%

    No Known Activations