© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15025
    Prev
    Next
    INDEX
    Explanations

    felt, MA, pseudo, Holl, foot

    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
    enne
    -0.24
    /place
    -0.21
    letal
    -0.21
    actories
    -0.20
     Bene
    -0.20
    pisa
    -0.20
    DRV
    -0.19
    çĸ¥
    -0.19
    URT
    -0.19
    .flush
    -0.18
    POSITIVE LOGITS
    çĿ¢
    0.21
    æĹłç¼ĺ
    0.21
    style
    0.21
    为éĩįçĤ¹
    0.20
    æł¡å¤ĸ
    0.19
    branch
    0.19
    è¿ĺä¸įæĺ¯
    0.19
    ISO
    0.19
    åħ¼é¡¾
    0.18
    æĶ»åĿļæĪĺ
    0.18
    Activations Density 0.150%

    No Known Activations