© 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. 14479
    Prev
    Next
    INDEX
    Explanations

    defense, AC, keeper, defence

    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
     needed
    -0.21
    ocity
    -0.20
    æĬ¹
    -0.20
    Needed
    -0.19
     Needed
    -0.19
    ocial
    -0.18
     needs
    -0.18
    大å¹ħ度
    -0.18
     Needs
    -0.18
     NEED
    -0.18
    POSITIVE LOGITS
    æĿ¥ä¸įåıĬ
    0.20
    åĩŃä»Ģä¹Ī
    0.19
    ResponseStatus
    0.18
    注æĦıåĬĽ
    0.18
    tsy
    0.18
     attent
    0.18
    æ·¦
    0.18
    å±Ĥå±Ĥ
    0.18
    зам
    0.18
    æĭĺ
    0.18
    Activations Density 0.027%

    No Known Activations