© 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. 12859
    Prev
    Next
    INDEX
    Explanations

    sentenced to prison or life

    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
    nid
    -0.19
    :border
    -0.19
    翳
    -0.18
    æĹºçĽĽ
    -0.18
    é¾ĭ
    -0.18
    AUSE
    -0.18
    çĻ¾å®¶
    -0.18
    EEP
    -0.17
     пÑĥÑĤеÑĪеÑģÑĤв
    -0.17
    pch
    -0.17
    POSITIVE LOGITS
    анÑĤ
    0.22
    æľĢé«ĺ
    0.20
    çĶŁæŃ»
    0.20
    åĨ°åĨ·
    0.19
    龸çİĭ
    0.18
    èIJ½ä¸ĭ
    0.18
    mans
    0.18
    åĪ¤åĨ³
    0.18
    æ°¸
    0.18
    anut
    0.17
    Activations Density 0.103%

    No Known Activations