© 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. 15605
    Prev
    Next
    INDEX
    Explanations

    months and life durations

    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
    åı¯æĥľ
    -0.28
    Unfortunately
    -0.24
    Sadly
    -0.24
     Unfortunately
    -0.23
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.22
     unfortunately
    -0.21
    åIJİæĤĶ
    -0.21
    大家ä¸Ģèµ·
    -0.20
    orsch
    -0.20
    宣æī¬
    -0.20
    POSITIVE LOGITS
     initially
    0.25
     until
    0.22
    缴åĪ°
    0.22
    Fortunately
    0.22
     midnight
    0.21
     initialValue
    0.21
    åĪĿæľŁ
    0.21
    åħĭæľį
    0.20
    èµ·åĪĿ
    0.20
    éķ¿è¾¾
    0.20
    Activations Density 0.207%

    No Known Activations