© 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. 14851
    Prev
    Next
    INDEX
    Explanations

    days and times

    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
     tick
    -0.23
    çľĭ好
    -0.22
    tick
    -0.21
    stant
    -0.20
    Tick
    -0.20
     ticks
    -0.19
    ticks
    -0.19
    ä¸īåĪĨ
    -0.19
    ç
    -0.18
     Goldberg
    -0.18
    POSITIVE LOGITS
    åĽŀå¿Ĩ
    0.24
    çº
    0.23
    åĽŀæĥ³
    0.21
    çĹĽ
    0.21
    æĥ³èµ·
    0.21
    ä¼ļå±ķ
    0.20
    追
    0.20
    è¿ĺ好
    0.20
     fault
    0.20
    ä¸Ģå¹´å¤ļ
    0.20
    Activations Density 0.291%

    No Known Activations