© 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. 11226
    Prev
    Next
    INDEX
    Explanations

    created by [name]

    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
    awl
    -0.23
    PTY
    -0.21
    erset
    -0.20
     vá»ijn
    -0.20
    à¸Ķา
    -0.20
    adium
    -0.20
    éĤ£ä¸Ģ
    -0.19
    eng
    -0.18
    enco
    -0.18
     ÅļwiÄĻt
    -0.18
    POSITIVE LOGITS
    çIJĨ
    0.23
    é¦ĸåıij
    0.20
    çĤ½
    0.19
    è±Ĩ
    0.19
    æ°´åĪ©å·¥ç¨ĭ
    0.19
    è¶´åľ¨
    0.19
    å°ıç¼ĸ
    0.18
    çIJ´
    0.18
    绣
    0.18
    ä¹IJåĽŃ
    0.18
    Activations Density 0.007%

    No Known Activations