© 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. 11575
    Prev
    Next
    INDEX
    Explanations

    filtering and sorting

    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
    两çĤ¹
    -0.19
     Hutchinson
    -0.19
    è¿ŀ线
    -0.18
    åģĥ
    -0.18
    aptors
    -0.18
    каÑĢ
    -0.18
    榻
    -0.18
     Norris
    -0.17
    oplan
    -0.17
     Launcher
    -0.17
    POSITIVE LOGITS
    çŃĽéĢī
    0.38
    /filter
    0.33
    è¿ĩ滤
    0.33
    çŃĽ
    0.28
    滤
    0.28
     lá»įc
    0.27
    åīĶ
    0.27
     filter
    0.27
     filtering
    0.27
     filters
    0.26
    Activations Density 0.104%

    No Known Activations