© 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. 13062
    Prev
    Next
    INDEX
    Explanations

    GTX or gtx

    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
    ground
    -0.24
     Guinness
    -0.20
    grounds
    -0.18
     ground
    -0.18
    æļij
    -0.18
     compensated
    -0.17
    æµĵæµĵ
    -0.17
    Tool
    -0.17
    tool
    -0.17
    GROUND
    -0.17
    POSITIVE LOGITS
    sWith
    0.20
    ä¸ĵ线
    0.18
    çĬ¬
    0.18
    ä¹Ļçĥ¯
    0.18
    .setLayoutParams
    0.17
    åİŁæ²¹
    0.17
    -league
    0.17
    åİŁå§ĭ
    0.17
    ç´§å¼ł
    0.17
    Modifier
    0.17
    Activations Density 0.003%

    No Known Activations