© 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. 13164
    Prev
    Next
    INDEX
    Explanations

    committing to relationships

    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
    èĤ²äºº
    -0.22
    大åħ¨
    -0.21
    à¹Ģสร
    -0.20
    hti
    -0.19
    æ±ĩ
    -0.19
    æĹłå£°
    -0.19
    æģ¯
    -0.19
    ç¨Ķ
    -0.19
    å½Ĵ
    -0.18
    å°Ĩ继ç»Ń
    -0.18
    POSITIVE LOGITS
     commitment
    0.29
     commit
    0.27
    commit
    0.26
     Commit
    0.26
     commitments
    0.24
     committing
    0.23
    åĽºå®ļ
    0.22
    .Commit
    0.21
     COMMIT
    0.20
    elp
    0.20
    Activations Density 0.016%

    No Known Activations