© 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. 11647
    Prev
    Next
    INDEX
    Explanations

    return or outcome

    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
    çŀ½
    -0.21
     Dop
    -0.21
    æ±¹
    -0.21
    åķŃ
    -0.20
     Yelp
    -0.19
     Fen
    -0.19
    ç¬Ħ
    -0.18
    è¦ģ害
    -0.18
    :update
    -0.18
     fre
    -0.18
    POSITIVE LOGITS
    çĻ¾åĪĨçĻ¾
    0.21
    åĨĽå·¥
    0.20
    gage
    0.19
    -hole
    0.19
    initializer
    0.18
    讲å¸Ī
    0.18
    æĭī
    0.18
    à¸Īร
    0.18
    igma
    0.18
    çĪĨ
    0.18
    Activations Density 0.001%

    No Known Activations