© 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. 15301
    Prev
    Next
    INDEX
    Explanations

    coyotes, wolves, lupus

    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
    åĶ§
    -0.22
    çŀ©çĽ®
    -0.18
    athi
    -0.17
    æ®ĸ
    -0.17
    indle
    -0.17
    çĶij
    -0.17
    åĮ»ç§ij大åѦ
    -0.16
    ertype
    -0.16
    ÙĤÙĪا
    -0.16
    é²Ķ
    -0.15
    POSITIVE LOGITS
    çĶŁæĢģä¿ĿæĬ¤
    0.19
     coy
    0.18
    éĿĴæµ·
    0.17
    西éĥ¨
    0.17
     lyn
    0.17
     ÑĤÑĢав
    0.17
    amen
    0.16
    ä¸Ńéĥ¨
    0.16
     lup
    0.16
     wilderness
    0.16
    Activations Density 0.008%

    No Known Activations