© 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. 48980
    Prev
    Next
    INDEX
    Explanations

    fertility and related contexts

    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
    inder
    -0.10
    ell
    -0.10
    à´Ł
    -0.08
    éĩ
    -0.08
    å¸
    -0.08
    yat
    -0.08
    åĦ¿
    -0.08
     toll
    -0.08
    r
    -0.08
    gn
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.10
    anded
    0.10
    ÙħÙĪÙĨ
    0.10
    å¤ł
    0.10
    ÙĬض
    0.10
    iously
    0.10
    濯
    0.09
    æ»Ĥ
    0.09
    è¿ĩåī©
    0.09
    ÙĬج
    0.09
    Activations Density 0.014%

    No Known Activations