© 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. 13620
    Prev
    Next
    INDEX
    Explanations

    suit your needs

    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
     bis
    -0.21
     Bout
    -0.19
    åĽłä¸ºä»ĸ
    -0.18
    vec
    -0.18
    éĿ¢ä¸´çĿĢ
    -0.18
    éĿ¢å¯¹
    -0.17
    iface
    -0.17
     Lair
    -0.17
    emd
    -0.17
    Sys
    -0.17
    POSITIVE LOGITS
    ings
    0.26
    å¿ĥæĦ¿
    0.22
    å®ŀéĻħæĥħåĨµ
    0.21
    å½ĵæŶçļĦ
    0.19
    ably
    0.19
    åIJĦæĸ¹
    0.18
    âĮ«
    0.18
    ingly
    0.18
    åĽ½æĥħ
    0.18
    çħ
    0.18
    Activations Density 0.005%

    No Known Activations