© 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. 12654
    Prev
    Next
    INDEX
    Explanations

    pickup trucks

    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°´æĻ¶
    -0.20
    iou
    -0.20
    uids
    -0.19
    copyright
    -0.19
    è¹¼
    -0.19
     spat
    -0.19
     Mig
    -0.19
    Stick
    -0.19
     Budapest
    -0.18
    ä¼Ľ
    -0.18
    POSITIVE LOGITS
     truck
    0.26
     trucks
    0.23
     Truck
    0.23
    åį¡è½¦
    0.23
    è£ħè½½
    0.22
    çĶ¨éĢĶ
    0.21
    aws
    0.21
    gricult
    0.21
    æĶ¯
    0.21
     Montana
    0.21
    Activations Density 0.017%

    No Known Activations