© 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. 12390
    Prev
    Next
    INDEX
    Explanations

    initialization or identifier

    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
    两人
    -0.21
    yte
    -0.21
    åį«
    -0.20
    sson
    -0.20
    hed
    -0.20
    åĿļ
    -0.20
    hamster
    -0.20
    lies
    -0.20
    èĮħ
    -0.20
    äººåľ¨
    -0.19
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½æĺ¯
    0.27
    è¿ĻäºĽä¸ľè¥¿
    0.22
    è¿Ļä¸ĢåĪĩ
    0.22
    椰
    0.22
     Rei
    0.20
    åĩłæŃ¥
    0.20
    è¿Ļåĩłä¸ª
    0.20
    çŃīå¤ļç§į
    0.20
    èħĭ
    0.19
    è¿ĻäºĽ
    0.19
    Activations Density 0.193%

    No Known Activations