© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10477
    Prev
    Next
    INDEX
    Explanations

    hostages, hijackings, standoff, robbery

    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
    Negative Logits
    sheets
    -0.21
    неÑģен
    -0.20
    -tm
    -0.20
    èĤł
    -0.19
     concatenated
    -0.19
    _EMIT
    -0.18
    æ©IJ
    -0.18
    åĬłä»¥
    -0.18
     полÑĥÑĩен
    -0.18
    欢åĸľ
    -0.18
    POSITIVE LOGITS
    æĪIJåĬŁçļĦ
    0.23
    æĪIJåĬŁ
    0.21
    éĥľ
    0.21
    åĬ«
    0.20
    æ´Ĺ
    0.20
    adors
    0.20
    ADOR
    0.19
    /host
    0.19
    ä¸Ģçķª
    0.19
     hostages
    0.19
    Activations Density 0.030%

    No Known Activations