© 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. 12480
    Prev
    Next
    INDEX
    Explanations

    pronouns and character names followed by verbs or subsequent names

    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
    人群
    -0.24
    è¿ĻäºĽäºº
    -0.22
    å¦Īå¦Ī
    -0.21
    é¢ł
    -0.21
    å«Ĥ
    -0.20
    碰
    -0.20
    èĢģ太太
    -0.19
    ivable
    -0.19
    '])[
    -0.19
    产å¦ĩ
    -0.19
    POSITIVE LOGITS
    æĺ¯ä»ĸ
    0.21
    æĬĬä»ĸ
    0.20
    åŁĭ
    0.20
    å®ŀéĻħæݧåĪ¶
    0.20
    imeo
    0.20
    è·Łä»ĸ
    0.20
    olls
    0.20
     counterpart
    0.20
    him
    0.20
    nid
    0.19
    Activations Density 0.047%

    No Known Activations