© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15255
    Prev
    Next
    INDEX
    Explanations

    self paced guided completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     cage
    -0.23
    leh
    -0.22
    åİį
    -0.21
    åIJ¨
    -0.21
    èĢĭ
    -0.21
    éĢħ
    -0.20
     cages
    -0.20
    .StatusCode
    -0.20
    è¿Ļå¼ł
    -0.20
    èį·
    -0.20
    POSITIVE LOGITS
    çļĦåŃ¦ä¹ł
    0.28
    åŃ¦ä¹ł
    0.27
    è¿Ľåº¦
    0.25
    åĩ½
    0.25
    _completion
    0.25
     learning
    0.24
    åѸç¿Ĵ
    0.23
    äºij端
    0.23
    modules
    0.23
    å®ĮæĪIJ
    0.23
    Activations Density 0.038%

    No Known Activations