© 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. 49144
    Prev
    Next
    INDEX
    Explanations

    age in years

    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
    .semantic
    -0.10
    çļĦå½¢å¼ı
    -0.09
    榷
    -0.09
    çĸ®
    -0.09
    HeaderCode
    -0.09
    ERSION
    -0.09
    ãĤ¹ãĥļãĥ¼ãĤ¹
    -0.09
    spNet
    -0.09
    ä¸Ģåı¥è¯Ŀ
    -0.08
    è¿Ļ段æŶéĹ´
    -0.08
    POSITIVE LOGITS
    éģIJ
    0.09
     age
    0.09
    age
    0.09
    weise
    0.09
     kiss
    0.08
    ings
    0.08
    AGR
    0.08
    _WP
    0.08
    ä¹į
    0.08
    heed
    0.08
    Activations Density 0.030%

    No Known Activations