© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10385
    Prev
    Next
    INDEX
    Explanations

    responsibility

    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
    人å±ħ
    -0.10
    Dot
    -0.09
    娼
    -0.08
    å«ī
    -0.08
    hoa
    -0.08
    Boot
    -0.08
    æģ¼
    -0.08
    ç®Ń
    -0.08
     Reese
    -0.08
    ç¬ij
    -0.08
    POSITIVE LOGITS
    责任
    0.22
     responsibility
    0.22
     responsibilities
    0.21
     Responsibility
    0.19
    çļĦ责任
    0.19
    責任
    0.18
    æī¿æĭħ责任
    0.17
     Responsibilities
    0.17
    责任æĦŁ
    0.17
    Respons
    0.16
    Activations Density 0.053%

    No Known Activations