© 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. 16810
    Prev
    Next
    INDEX
    Explanations

    course descriptions

    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
    /Instruction
    -0.21
    orphic
    -0.20
    ActionTypes
    -0.20
    lish
    -0.19
    çĿIJ
    -0.19
    åįıä¼ļä¼ļåijĺ
    -0.19
     Hü
    -0.19
     din
    -0.19
    伺
    -0.19
    ategorized
    -0.19
    POSITIVE LOGITS
    åħ¨æĹ¥åĪ¶
    0.23
    åı¯ä¾Ľ
    0.23
    æļij
    0.21
    ç¡ķ士
    0.21
    åģĩæľŁ
    0.21
     parc
    0.20
    ç¡ķ
    0.20
    å¼ij
    0.20
    çĪµå£«
    0.20
     disap
    0.20
    Activations Density 0.044%

    No Known Activations