© 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. 56655
    Prev
    Next
    INDEX
    Explanations

    decision to make

    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
    é¢Ĩä¼ļ
    -0.11
    ATALOG
    -0.09
    çļ®èĤ¤çĹħ
    -0.09
    大å¸Ī
    -0.09
    ulen
    -0.09
    _UC
    -0.09
    æĨ
    -0.09
    ocos
    -0.09
    stor
    -0.08
    éĤĪ
    -0.08
    POSITIVE LOGITS
    åĨ³çŃĸ
    0.17
    åĨ³å®ļ
    0.16
     decisions
    0.16
     decision
    0.16
     Decision
    0.14
    decision
    0.13
    決å®ļ
    0.13
    æĬīæĭ©
    0.13
    Decision
    0.13
     deciding
    0.13
    Activations Density 0.074%

    No Known Activations