© 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. 8861
    Prev
    Next
    INDEX
    Explanations

    make informed decisions

    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
    lazy
    -0.11
    çī¹åĪ«å£°æĺİ
    -0.10
    åĬ¡
    -0.09
    ä¼ģ
    -0.09
    çĴ©
    -0.09
    еÑĤÑĮ
    -0.09
    _COMPAT
    -0.09
    åĸĩåıŃ
    -0.09
    _lazy
    -0.09
    æłĩæĺİ
    -0.09
    POSITIVE LOGITS
     informed
    0.14
     decisions
    0.11
    æĬīæĭ©
    0.10
    4
    0.10
    5
    0.09
    1
    0.09
    6
    0.09
    3
    0.09
    åĨ³å®ļ
    0.09
    7
    0.09
    Activations Density 0.029%

    No Known Activations