© 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. 10584
    Prev
    Next
    INDEX
    Explanations

    location or position

    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
    olk
    -0.20
    ÑĢенд
    -0.20
    irma
    -0.20
    liga
    -0.20
    edium
    -0.20
    使çĶ¨æĿĥ
    -0.19
    getExtension
    -0.19
    æĺ¯å¦Ĥä½ķ
    -0.19
    _sink
    -0.18
    åıĮæīĭ
    -0.18
    POSITIVE LOGITS
    æĿ¥è®²
    0.24
    产ä¸ļéĵ¾
    0.20
    iu
    0.19
    èĩªçĦ¶çķĮ
    0.19
    ä»ĭ
    0.19
    åĮĸ解
    0.19
     constellation
    0.18
    åıªè§ģ
    0.18
    วà¸ĩ
    0.18
    transactions
    0.18
    Activations Density 0.046%

    No Known Activations