© 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. 14386
    Prev
    Next
    INDEX
    Explanations

    detained, tortured, imprisoned, disappeared, forced

    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
    害ç¾ŀ
    -0.23
    åı¯æĥľ
    -0.21
    çīµæīĭ
    -0.21
    ä¼IJ
    -0.20
    åĬ¿å¤´
    -0.20
     halves
    -0.20
    ÑģÑĤолÑĮ
    -0.20
    æĢİä¹Īçľĭ
    -0.19
    çģ¾åĮº
    -0.19
    大家åĪĨ享
    -0.19
    POSITIVE LOGITS
    nda
    0.21
    .JSON
    0.21
    ella
    0.21
    анÑĤ
    0.21
    _WM
    0.20
    .resp
    0.20
    cka
    0.20
     custody
    0.19
    çŃīå¾ħ
    0.19
    è¾±
    0.19
    Activations Density 0.017%

    No Known Activations