© 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. 16905
    Prev
    Next
    INDEX
    Explanations

    empty, vacant, or null state

    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
    andel
    -0.20
    ä¸įåIJĮ
    -0.18
    opp
    -0.18
     Malk
    -0.17
    æľ¬ç½ij
    -0.17
    redd
    -0.17
    iterated
    -0.17
    ä»»æĦı
    -0.16
    è¿Ń代
    -0.16
    éļı便
    -0.16
    POSITIVE LOGITS
    ness
    0.35
    /null
    0.24
    (empty
    0.24
    空
    0.23
    /false
    0.23
    /full
    0.22
    /un
    0.22
    -eyed
    0.21
    çĶŁäº§èĥ½åĬĽ
    0.21
    -handed
    0.21
    Activations Density 0.072%

    No Known Activations