© 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. 16830
    Prev
    Next
    INDEX
    Explanations

    value and purpose

    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
    è¿ĻäºĽéĹ®é¢ĺ
    -0.23
    è¿Ļæł·åģļ
    -0.22
    noinspection
    -0.21
    缸éĹľæľįåĭĻ
    -0.20
    ä¼ģä¸ļåĴĮ
    -0.20
    åħ¶å®ĥéĹ®é¢ĺ
    -0.19
    两次
    -0.19
    ibraries
    -0.19
    çī¹åĪ«å£°æĺİ
    -0.19
    åIJĦ个çݯèĬĤ
    -0.18
    POSITIVE LOGITS
     value
    0.29
     purpose
    0.23
    (Initialized
    0.22
     energy
    0.21
    atum
    0.21
     hope
    0.21
     potential
    0.21
     worth
    0.21
     direction
    0.20
     balance
    0.20
    Activations Density 0.171%

    No Known Activations