© 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. 12423
    Prev
    Next
    INDEX
    Explanations

    -ment suffix

    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
    er
    -0.28
    itional
    -0.25
    ities
    -0.22
    ../../../
    -0.22
    åĮĸçļĦ
    -0.21
    -0.20
    åĮĸè¿Ľç¨ĭ
    -0.20
    ically
    -0.20
    缮ãģ®
    -0.20
    erator
    -0.20
    POSITIVE LOGITS
    ioned
    0.21
    ëĭĪëĭ¤
    0.18
    asure
    0.18
    illet
    0.17
    /vnd
    0.17
    ype
    0.17
    orage
    0.17
    te
    0.17
    orado
    0.16
    orra
    0.16
    Activations Density 0.081%

    No Known Activations