© 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. 16602
    Prev
    Next
    INDEX
    Explanations

    List of, Q:

    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
    并ä¸įå¤ļ
    -0.23
    è¾Ļ
    -0.21
    å§Ķç»Ħç»ĩéĥ¨
    -0.19
    ecret
    -0.19
    çķ¢
    -0.19
    /stream
    -0.19
     circum
    -0.18
    æѤæ¡Ī
    -0.18
    éĴµ
    -0.18
    æ¯ķ
    -0.18
    POSITIVE LOGITS
    isl
    0.21
    æĪĸ
    0.21
    bst
    0.20
     advice
    0.20
    ugs
    0.20
    uten
    0.20
     BDS
    0.19
    Unsafe
    0.19
     Advice
    0.19
    å¿ĺ
    0.19
    Activations Density 0.005%

    No Known Activations