© 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. 16345
    Prev
    Next
    INDEX
    Explanations

    360

    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
    lish
    -0.19
    igers
    -0.16
    ogany
    -0.16
     deliver
    -0.16
    isi
    -0.16
    ewan
    -0.15
    Äĥng
    -0.15
    åįģåĪĨ
    -0.15
    eten
    -0.15
    æ³Ľ
    -0.15
    POSITIVE LOGITS
    å±ģ
    0.20
    ç½ijé¦ĸ页
    0.19
    èµ
    0.19
    ÑģÑĤÑĢа
    0.19
    åħ¶å®ĥéĹ®é¢ĺ
    0.19
    ãģĤãĤĭç¨ĭ度
    0.18
    çĿĩ
    0.18
    è°ĥåij³
    0.18
    å½±ä¸ļ
    0.18
    屿
    0.18
    Activations Density 0.011%

    No Known Activations