© 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. 13941
    Prev
    Next
    INDEX
    Explanations

    aviation and aircraft topics

    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
     crews
    -0.22
    é³Ŀ
    -0.20
    éķ°
    -0.20
    Tier
    -0.20
    Cargo
    -0.20
    /lg
    -0.20
    umbo
    -0.19
    éºŁ
    -0.18
    çĤ·
    -0.18
     cargo
    -0.18
    POSITIVE LOGITS
    çĶ¨åĵģ
    0.22
    ä¸Ģæĸ¹
    0.20
    _singular
    0.19
    -ish
    0.19
    åİĨåı²æĢ§
    0.19
    elsen
    0.19
    ä¸įåĬ¨äº§
    0.19
    пÑĢакÑĤик
    0.19
    ://%
    0.18
    jee
    0.18
    Activations Density 0.009%

    No Known Activations