© 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. 1553
    Prev
    Next
    INDEX
    Explanations

    knowledge representation, semantic hierarchy, structured data

    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
     extortion
    -0.29
     forfe
    -0.28
     tuition
    -0.28
    åĻ¨æĿIJ
    -0.27
    Projectile
    -0.27
    .timeout
    -0.26
    éĢģåĩº
    -0.25
     fluids
    -0.24
     grinding
    -0.24
    downloads
    -0.24
    POSITIVE LOGITS
     Semantic
    0.47
     semantic
    0.43
     hierarchical
    0.42
     hier
    0.41
     ontology
    0.41
     hierarchy
    0.40
    Semantic
    0.39
    Hier
    0.38
    ä½ĵç³»
    0.37
     Hier
    0.36
    Activations Density 0.127%

    No Known Activations