© 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. 16075
    Prev
    Next
    INDEX
    Explanations

    street, city, state, zip code

    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
    ä»Ĺ
    -0.21
    æĴŀ
    -0.21
    åĬ¡
    -0.21
    å¯Ĥ
    -0.20
    ihat
    -0.19
     Stamford
    -0.19
    erten
    -0.19
     Harden
    -0.18
    æĽ´æĸ°
    -0.18
    æݨåIJij
    -0.18
    POSITIVE LOGITS
    _ring
    0.19
    .qual
    0.19
    ohl
    0.19
    å°§
    0.19
    çĶ»åį·
    0.18
    ç¼ĺ
    0.17
    ç·£
    0.17
    çļĦ好å¤Ħ
    0.17
     couch
    0.17
    .getRandom
    0.17
    Activations Density 0.014%

    No Known Activations