© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16292
    Prev
    Next
    INDEX
    Explanations

    Lodge

    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
    [opt
    -0.23
    诮
    -0.23
    çĥ
    -0.20
    迹
    -0.19
    illet
    -0.19
    CLS
    -0.19
    éĺ»
    -0.19
     carniv
    -0.18
     доÑģÑĤ
    -0.18
    lett
    -0.18
    POSITIVE LOGITS
    RIA
    0.20
    è¿Ľåº¦
    0.20
     Peb
    0.19
    èµĦæºIJæķ´åIJĪ
    0.19
    åĩ¤
    0.18
    asonic
    0.18
    è®®
    0.18
    treeview
    0.18
    tek
    0.18
     JObject
    0.18
    Activations Density 0.002%

    No Known Activations