© 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. 13137
    Prev
    Next
    INDEX
    Explanations

    died or death from injuries

    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
    iture
    -0.23
    gil
    -0.22
     scrim
    -0.21
    éĹ²
    -0.20
    æļĤ
    -0.20
    FRING
    -0.19
    çªģåıij
    -0.19
     anecd
    -0.19
    常常
    -0.19
     grad
    -0.19
    POSITIVE LOGITS
    å½ĵæĻļ
    0.25
    å½ĵ天
    0.23
    å½ĵåį³
    0.23
    _ble
    0.23
    èĦı
    0.21
    ÑģмеÑĢÑĤ
    0.21
    uby
    0.21
    å½ĵæĹ¥
    0.21
    å³Ĵ
    0.20
    cro
    0.20
    Activations Density 0.027%

    No Known Activations