© 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. 14773
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames or possessives

    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
    é«ĵ
    -0.21
    zeich
    -0.18
    ä»ĸ们ä¼ļ
    -0.18
    /releases
    -0.18
    åİŁåĪĽ
    -0.18
    errar
    -0.17
    å±Ĥåĩºä¸įç©·
    -0.17
    è¯ķçĤ¹
    -0.17
    iaux
    -0.17
    åĽłåľ°åĪ¶å®ľ
    -0.17
    POSITIVE LOGITS
    Acc
    0.21
    anus
    0.20
    è¿Ļè¾¹
    0.19
    çĬį
    0.19
    ä¸įæĺ¯ä¸Ģ个
    0.18
    otron
    0.18
    inski
    0.18
    Daily
    0.17
    osphere
    0.17
    assing
    0.17
    Activations Density 0.074%

    No Known Activations