© 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. 12332
    Prev
    Next
    INDEX
    Explanations

    bit of / bit more

    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
    äºĨä¸Ģéģį
    -0.20
    ãģ¾ãģļãģ¯
    -0.19
    adian
    -0.18
    bidden
    -0.17
    /OR
    -0.17
    ived
    -0.17
    ä¸Ģéģį
    -0.17
    BOR
    -0.16
     غاÙĦ
    -0.16
     suá»ijt
    -0.16
    POSITIVE LOGITS
    ìĶ©
    0.28
    ÑĩиÑģлен
    0.20
    -known
    0.20
    ting
    0.20
    åĦ¿
    0.19
    ness
    0.19
    /all
    0.18
    tern
    0.18
    积èĵĦ
    0.18
    åħ¶ä»ĸçļĦ
    0.18
    Activations Density 0.017%

    No Known Activations