© 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. 13315
    Prev
    Next
    INDEX
    Explanations

    alphanumeric IDs and hashes

    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
    æ³³
    -0.23
    æĦıè§ģåıįé¦Ī
    -0.21
    ä¸ĭä¸ĢæŃ¥
    -0.19
    å®Įå·¥
    -0.17
    UnderTest
    -0.17
    __$
    -0.17
     downgrade
    -0.17
     Upgrade
    -0.17
    缸çķ¶
    -0.17
    /gui
    -0.17
    POSITIVE LOGITS
     bon
    0.20
    åIJijå¤ĸ
    0.19
     Obl
    0.19
     gob
    0.19
    .AP
    0.18
    ega
    0.18
     Cuisine
    0.18
    ere
    0.17
     pole
    0.17
     thought
    0.17
    Activations Density 0.204%

    No Known Activations