© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37245
    Prev
    Next
    INDEX
    Explanations

    age and over

    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
    å°ıå§IJå§IJ
    -0.09
    åħĭæľį
    -0.08
    URED
    -0.08
    eli
    -0.08
    asio
    -0.08
    çĺ¾
    -0.08
    quiet
    -0.08
    çIJ
    -0.08
     Whip
    -0.08
     Pics
    -0.08
    POSITIVE LOGITS
     onwards
    0.16
    以æĿ¥
    0.15
    以ä¾Ĩ
    0.13
    å¾ĢåIJİ
    0.13
    以ä¸ĬçļĦ
    0.13
    åıĬ以ä¸Ĭ
    0.12
    以åIJİ
    0.12
    年以æĿ¥
    0.12
    以å¾Į
    0.12
    å²ģ以ä¸Ĭ
    0.12
    Activations Density 0.080%

    No Known Activations