© 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. 11577
    Prev
    Next
    INDEX
    Explanations

    display technology

    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
    èįīåľ°
    -0.20
    party
    -0.20
    å°±è¿Ļä¹Ī
    -0.19
     окол
    -0.19
    ä¸įå°ı
    -0.19
    åIJİæĤĶ
    -0.18
    æīij
    -0.18
    AGED
    -0.17
    unta
    -0.17
    rule
    -0.17
    POSITIVE LOGITS
    enie
    0.21
    æ½¼
    0.20
    çī¢
    0.20
    arters
    0.20
    éĺ´éĺ³
    0.19
    ¹Ħ
    0.19
    æ¹Ħ
    0.19
    ç¼
    0.19
    缤
    0.18
    Radians
    0.18
    Activations Density 0.003%

    No Known Activations