© 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. 13304
    Prev
    Next
    INDEX
    Explanations

    active and passive characteristics

    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
     sourceMapping
    -0.22
     pornost
    -0.21
     mainBundle
    -0.20
    è¿Ļä¸ĢçĤ¹
    -0.20
    traîn
    -0.20
     münchen
    -0.20
     overposting
    -0.19
    ê±į
    -0.19
    uez
    -0.19
    íĹĢ
    -0.19
    POSITIVE LOGITS
     alike
    0.38
    çıįçıł
    0.22
    gos
    0.21
     striped
    0.19
    lite
    0.19
    vie
    0.19
    éĥ½éĿŀ常
    0.18
    缸ç»ĵåIJĪ
    0.18
    ä½¥
    0.18
    averse
    0.17
    Activations Density 0.173%

    No Known Activations