© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37012
    Prev
    Next
    INDEX
    Explanations

    sneak peek

    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
    ç®ĬæĥħåĨµ
    -0.09
    anova
    -0.09
    ination
    -0.09
    符åı·
    -0.08
    çĸ¤
    -0.08
    å¿ĥæĥħ
    -0.08
    GuidId
    -0.08
    essed
    -0.08
    æľīèĥ½åĬĽ
    -0.08
    å½»åºķ
    -0.08
    POSITIVE LOGITS
    ously
    0.11
    ç½ķ
    0.11
    ernet
    0.09
    ishly
    0.09
     Peek
    0.09
    庵
    0.09
    æĿ¥çļĦ
    0.09
    ly
    0.09
    -cut
    0.09
    gram
    0.08
    Activations Density 0.004%

    No Known Activations