© 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. 14868
    Prev
    Next
    INDEX
    Explanations

    munitions and bombs

    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
     Incoming
    -0.21
    åŃ£
    -0.21
    ewire
    -0.20
    inely
    -0.20
    æ·ĺ
    -0.20
    é£İåIJ¹
    -0.20
     servant
    -0.20
    emade
    -0.19
    è§ī
    -0.19
    ozy
    -0.18
    POSITIVE LOGITS
    æĬķæĶ¾
    0.29
     payload
    0.27
    éĩĬæĶ¾
    0.23
    payload
    0.23
    _payload
    0.22
     payloads
    0.22
     disposition
    0.22
    (payload
    0.21
     deliver
    0.21
    attach
    0.21
    Activations Density 0.030%

    No Known Activations