© 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. 16923
    Prev
    Next
    INDEX
    Explanations

    police and sheriff's department actions

    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
    对æīĭ
    -0.21
     filib
    -0.21
    .getHeader
    -0.19
    æ·±å¤Ħ
    -0.18
    æ´ģ
    -0.18
    çŧ
    -0.18
     terra
    -0.18
    建åĨĽ
    -0.17
    Cleaning
    -0.17
    æ»ļæ»ļ
    -0.17
    POSITIVE LOGITS
    åĴĮ社ä¼ļ
    0.23
    伺
    0.21
    Ring
    0.20
     Moor
    0.19
     nearby
    0.19
    neau
    0.18
     Nearby
    0.18
    âİ
    0.18
     OSI
    0.18
     ring
    0.18
    Activations Density 0.034%

    No Known Activations