© 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. 1858
    Prev
    Next
    INDEX
    Explanations

    protrusion, circular, axial, portions

    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
     unofficial
    -0.31
     privat
    -0.30
     Internet
    -0.28
     practiced
    -0.27
     Certified
    -0.27
     nouve
    -0.27
     curated
    -0.27
     genuinely
    -0.27
     sponsored
    -0.27
     mission
    -0.26
    POSITIVE LOGITS
     protr
    0.47
    伸åĩº
    0.42
     thickness
    0.41
     cylindrical
    0.40
    顶éĥ¨
    0.39
     perpendicular
    0.38
     axial
    0.38
     spacer
    0.37
    è¿ŀæİ¥
    0.36
     outer
    0.36
    Activations Density 0.549%

    No Known Activations