© 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. 16223
    Prev
    Next
    INDEX
    Explanations

    `ex-gay` and `sin`

    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
    享åıĹåĪ°
    -0.22
    åĪĥ
    -0.22
    该åİ¿
    -0.21
    享åıĹ
    -0.21
    æĮĩçĶ²
    -0.20
    ä¿Ŀéļľ
    -0.20
    åĬŀäºĭ
    -0.20
    çľ¼åħī
    -0.20
    æĭīåĬ¨
    -0.20
    è¿Ļä¸Ģ次
    -0.20
    POSITIVE LOGITS
    æ²»çĸĹæĸ¹æ³ķ
    0.24
     vol
    0.22
    (vol
    0.21
     ps
    0.20
    Vol
    0.20
    .vol
    0.20
    InputLabel
    0.20
    (ps
    0.20
    Convertible
    0.20
     Jew
    0.19
    Activations Density 0.016%

    No Known Activations