© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15345
    Prev
    Next
    INDEX
    Explanations

    altitude

    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
    æĦıä¹īä¸Ĭ
    -0.20
    èĢģ乡
    -0.19
    éªł
    -0.19
     Mister
    -0.19
    å±¹
    -0.18
    åĨ¥
    -0.18
    æ³°
    -0.18
    ä¸įæĪIJ
    -0.18
    è¿Ļæł·çļĦè¯Ŀ
    -0.18
    ä¸ĢçĤ¹éĥ½ä¸į
    -0.18
    POSITIVE LOGITS
    ACS
    0.21
    ietf
    0.20
    æİ¥éĢģ
    0.19
    éĢı
    0.19
    hower
    0.19
    ç¥ŀ
    0.18
    æ·±åħ¥
    0.18
    thora
    0.18
     presses
    0.17
    åĨ²
    0.17
    Activations Density 0.012%

    No Known Activations