© 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. 16311
    Prev
    Next
    INDEX
    Explanations

    toll free, hotline, call, today, email

    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
    è¶³å¤Ł
    -0.19
    åķ
    -0.18
    Reality
    -0.18
    acey
    -0.18
    æĪIJåĵģ
    -0.18
    Seen
    -0.17
    çĪº
    -0.17
    _third
    -0.17
    third
    -0.17
    seen
    -0.17
    POSITIVE LOGITS
     bevor
    0.19
    descriptor
    0.18
    åIJĪèµĦ
    0.18
     Rear
    0.18
    äºĪ以
    0.18
    èħij
    0.17
    åį°
    0.17
    好æĦŁ
    0.17
    lez
    0.17
    æĸ¹å¼ıè¿Ľè¡Į
    0.17
    Activations Density 0.004%

    No Known Activations