© 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. 11411
    Prev
    Next
    INDEX
    Explanations

    roleplay and story chapters

    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
    âĸ¡
    -0.21
     insider
    -0.20
    orf
    -0.20
     insiders
    -0.19
     editions
    -0.19
    .matcher
    -0.19
     economist
    -0.18
     nutshell
    -0.18
     pattern
    -0.18
    %m
    -0.18
    POSITIVE LOGITS
    模æĭŁ
    0.27
    æī®æ¼Ķ
    0.24
    è§Ĵèī²
    0.23
    çī©æµģåħ¬åı¸
    0.23
    индивид
    0.23
    еÑģÑĤеÑģÑĤвенн
    0.23
    仿
    0.23
    缮åīįå·²ç»ı
    0.22
    ä¸ĵå±ŀ
    0.22
    ä¸ĸçķĮè§Ĥ
    0.22
    Activations Density 0.047%

    No Known Activations