© 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. 12175
    Prev
    Next
    INDEX
    Explanations

    road names and numbers

    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
    елÑĮ
    -0.21
    éĢłåģĩ
    -0.18
    EntryPoint
    -0.18
    биÑĢ
    -0.18
    åģľçīĮ
    -0.18
     sausage
    -0.18
     barrel
    -0.17
     rpm
    -0.17
    OrNil
    -0.17
    callee
    -0.17
    POSITIVE LOGITS
    éģĵè·¯
    0.22
    éĦł
    0.22
     roads
    0.21
    è·¯å¾Ħ
    0.20
     ÐŁÐ¾Ñĩем
    0.20
    ç¼ij
    0.20
    .routes
    0.20
    æĶ¹
    0.19
    æ¡¥æ¢ģ
    0.19
    æ´½
    0.19
    Activations Density 0.015%

    No Known Activations