© 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. 15754
    Prev
    Next
    INDEX
    Explanations

    police officers and pursuits

    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
    å°ijäºĨ
    -0.21
     sentimental
    -0.20
    ordinate
    -0.20
    :index
    -0.19
    ussy
    -0.19
    å¹ħ度
    -0.19
    =index
    -0.18
    shelf
    -0.18
    æ¶ĪåĮĸ
    -0.18
    /stat
    -0.18
    POSITIVE LOGITS
    第ä¸Ģæī¹
    0.24
    梯éĺŁ
    0.22
    é¦ĸæī¹
    0.21
    ä¾Ŀæ³ķ追究
    0.20
    èī°è¾Ľ
    0.20
    å°±è¿ij
    0.20
    åįļæĸĩ
    0.20
    åħ¥æĪ·
    0.19
    åĪ°æĿ¥
    0.19
    éĺ»æŃ¢
    0.19
    Activations Density 0.023%

    No Known Activations