© 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. 13041
    Prev
    Next
    INDEX
    Explanations

    beyond words

    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
    èĽĽ
    -0.22
    åŁºè°ĥ
    -0.21
    线索
    -0.20
    -dismiss
    -0.20
    -picker
    -0.19
    _wire
    -0.19
    ickers
    -0.18
    æĩ¦
    -0.18
    Party
    -0.18
    .AllowUser
    -0.18
    POSITIVE LOGITS
    ä¹ŁæĹłæ³ķ
    0.23
    æ´Ļ
    0.19
     how
    0.19
     Hut
    0.19
     undo
    0.19
    çļĦåľ°æŃ¥
    0.18
    éĥ½æĹłæ³ķ
    0.18
    Undo
    0.18
    venience
    0.18
    太å¤ļçļĦ
    0.18
    Activations Density 0.025%

    No Known Activations