© 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. 15756
    Prev
    Next
    INDEX
    Explanations

    said, quoted, however, back

    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
    лад
    -0.20
    èµİ
    -0.20
    å®ļäºĨ
    -0.19
    åijĹ
    -0.19
    çģ¯çģ«
    -0.19
    ลา
    -0.19
    åħ·
    -0.19
    _ca
    -0.19
     обÑıзан
    -0.18
    åIJı
    -0.18
    POSITIVE LOGITS
    解éĩĬ
    0.25
    outing
    0.22
     argument
    0.22
    cı
    0.21
     arguments
    0.21
    ç»´æĬ¤
    0.20
     drowned
    0.19
    论è¯ģ
    0.19
     defending
    0.19
    mith
    0.19
    Activations Density 0.094%

    No Known Activations