© 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. 50149
    Prev
    Next
    INDEX
    Explanations

    professional labeling, medical effects

    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
    åŃIJéĩĮ
    -0.09
    è¿ĩäºĨ
    -0.08
    å¾ĪæŃ£å¸¸
    -0.08
    çĮ©
    -0.08
    åĴĮåıijå±ķ
    -0.08
    Formatter
    -0.08
    åģıå·®
    -0.08
    (normal
    -0.08
    uet
    -0.08
    ç¹ģ
    -0.08
    POSITIVE LOGITS
    owy
    0.11
    è´Łè´£ä»»
    0.09
    注æĺİåĩºå¤Ħ
    0.09
    å¼ķæµģ
    0.09
    諮詢
    0.08
    .Scheme
    0.08
    OOM
    0.08
    ãĤ½ãĥ¼
    0.08
    alers
    0.08
    _instructions
    0.08
    Activations Density 0.003%

    No Known Activations