© 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. 13048
    Prev
    Next
    INDEX
    Explanations

    socialist, Ron, video, LA, trade, Santa

    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
    触
    -0.21
     него
    -0.21
    esting
    -0.19
    nÃŃ
    -0.17
    _sid
    -0.17
    ENCH
    -0.17
    éĩĩåıĸ
    -0.17
    ä»ĸèĩªå·±
    -0.17
    ograd
    -0.17
     Chandler
    -0.17
    POSITIVE LOGITS
    TRS
    0.22
    è¢Ī
    0.20
    éĢģåĪ°
    0.19
    è¯ģ
    0.19
    éĤ£ä½į
    0.19
    çĻ½çĻ½
    0.19
    åĭº
    0.18
    家ä½ı
    0.18
    æīĢè°ĵçļĦ
    0.18
    榻
    0.18
    Activations Density 0.244%

    No Known Activations