© 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. 2651
    Prev
    Next
    INDEX
    Explanations

    neutron absorption, scattering, shield

    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
    åħ®
    -0.22
    åŀł
    -0.21
    åľ¨èģĮ
    -0.21
     chắn
    -0.21
    è£Ļ
    -0.21
    <Func
    -0.21
    çĶ¨æīĭ
    -0.20
    и
    -0.20
    ITCH
    -0.20
    åħĪæĺ¯
    -0.20
    POSITIVE LOGITS
    ality
    0.22
    廪
    0.22
     ideally
    0.21
    å¯Ŀ室
    0.21
    ass
    0.21
    agli
    0.21
    kid
    0.21
     Yard
    0.21
    bone
    0.20
    çIJĨæĥ³
    0.20
    Activations Density 0.007%

    No Known Activations