© 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. 13026
    Prev
    Next
    INDEX
    Explanations

    ISBN

    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
    ä¸Ģç¬Ķ
    -0.23
    ä»İèĢĮ使
    -0.21
    次æķ°
    -0.20
    æ¯ı次éĥ½
    -0.20
    çŁ
    -0.20
    媳
    -0.20
    marvin
    -0.19
    è¿Ļä¸Ģ次
    -0.19
    èİ«
    -0.19
    TON
    -0.18
    POSITIVE LOGITS
     isbn
    0.24
     Kou
    0.24
    isbn
    0.21
    ckt
    0.21
    ISBN
    0.20
    ä¸įæĺĵ
    0.20
    reten
    0.20
    åĩºçīĪ
    0.20
     Feld
    0.19
    æŃ£æĸĩ
    0.19
    Activations Density 0.007%

    No Known Activations