© 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. 20622
    Prev
    Next
    INDEX
    Explanations

    genealogy record information

    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
    (term
    -0.10
    ãĥĪãĥ«
    -0.09
    .sul
    -0.09
    ä¾ij
    -0.09
    æĭ¥
    -0.09
    erring
    -0.09
    вÑĥ
    -0.09
    ·æĸ°
    -0.09
    æīª
    -0.09
    责任ç¼ĸè¾ij
    -0.09
    POSITIVE LOGITS
     hanging
    0.09
    æĻºåķĨ
    0.09
     digit
    0.08
    åĮĸå¦Ĩ
    0.08
    龸
    0.08
     Digit
    0.08
    ewing
    0.08
    æŀŃ
    0.08
    æĻºèĥ½åĮĸ
    0.08
    adows
    0.08
    Activations Density 0.038%

    No Known Activations