© 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. 12646
    Prev
    Next
    INDEX
    Explanations

    fuel and combustible products

    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
    æ¡Ĩ
    -0.23
    dsa
    -0.22
    åŃķ
    -0.21
    åĩºè¡Ģ
    -0.21
    éĶĩ
    -0.21
    yon
    -0.21
    åİĭè¿«
    -0.20
    çĶŁæ®ĸ
    -0.20
    åĥıç´ł
    -0.20
    .commons
    -0.20
    POSITIVE LOGITS
    æ··åIJĪ
    0.27
     combust
    0.26
     mixture
    0.25
    æ±½
    0.24
     combustion
    0.24
     NASCAR
    0.23
    çĩĥçĥ§
    0.23
    æݺ
    0.22
    çĩĥæ²¹
    0.22
     gasoline
    0.22
    Activations Density 0.022%

    No Known Activations