© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1445
    Prev
    Next
    INDEX
    Explanations

    guarding or protecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    çĺ¦èº«
    -0.26
    åĪĨæľŁ
    -0.24
    ĻĤ
    -0.23
    审
    -0.23
    åĩ¡äºĭ
    -0.22
     ÑĢа
    -0.22
     serial
    -0.21
     scoring
    -0.21
    ä¼łçľŁ
    -0.21
     selections
    -0.21
    POSITIVE LOGITS
    ä¿ĿæĬ¤
    0.59
    ä¿Ŀåį«
    0.52
    ä¿ĿèŃ·
    0.50
     protect
    0.48
     protection
    0.47
     protecting
    0.46
    å®ĪæĬ¤
    0.44
     Protection
    0.43
     protects
    0.43
     protector
    0.43
    Activations Density 0.031%

    No Known Activations