© 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. 13433
    Prev
    Next
    INDEX
    Explanations

    attorney lists

    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
    asis
    -0.21
    .EN
    -0.18
     quarters
    -0.18
    èĵ¬åĭĥ
    -0.18
    ä¹ĭç±»çļĦ
    -0.18
    åįĥéĩĮ
    -0.18
    .Manifest
    -0.18
    anim
    -0.18
     enrol
    -0.18
    åľ¨è¿Ļ个
    -0.17
    POSITIVE LOGITS
    ISTR
    0.22
    IZER
    0.22
    COPE
    0.21
    ECH
    0.20
    elib
    0.19
    ANGER
    0.19
    ä¸įåıĺ
    0.19
    põe
    0.19
    ?url
    0.18
    .payload
    0.18
    Activations Density 0.111%

    No Known Activations