© 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. 11923
    Prev
    Next
    INDEX
    Explanations

    making or changing 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
    laughter
    -0.09
    ä¹±
    -0.08
     sk
    -0.08
    urrences
    -0.08
    LBL
    -0.08
    驽
    -0.08
    æĹł
    -0.08
    æĴĩ
    -0.08
    uhe
    -0.08
     synd
    -0.08
    POSITIVE LOGITS
    åĨ³å®ļ
    0.21
    åĨ³å®ļäºĨ
    0.18
    決å®ļ
    0.18
     decided
    0.17
    åĨ³å¿ĥ
    0.17
    çļĦåĨ³å¿ĥ
    0.16
    主æĦı
    0.16
     decide
    0.15
     decision
    0.15
     decisión
    0.14
    Activations Density 0.042%

    No Known Activations