© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15037
    Prev
    Next
    INDEX
    Explanations

    Gamma Knife, King, Will

    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
    ogan
    -0.19
    åĪĽæĦı
    -0.19
    çļĦåľ°åĽ¾
    -0.18
    åķĨåѦéĻ¢
    -0.18
    mith
    -0.18
    çŃ·
    -0.18
    ResponseBody
    -0.17
    [js
    -0.17
    éĻįå¹ħ
    -0.17
    ä¸Ńæĸ°
    -0.17
    POSITIVE LOGITS
    å¸ĥé²ģ
    0.20
    ussian
    0.19
    asty
    0.19
    èĢģ人
    0.19
    antal
    0.19
    rede
    0.19
    zy
    0.18
    chat
    0.18
    (&_
    0.18
    perf
    0.17
    Activations Density 0.003%

    No Known Activations