© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12606
    Prev
    Next
    INDEX
    Explanations

    course of action

    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
    бÑĭÑĤ
    -0.21
    è´Łèį·
    -0.20
    ToWorld
    -0.19
    é»ijåIJįåįķ
    -0.19
    thresh
    -0.19
    /rfc
    -0.19
    忾
    -0.18
    lice
    -0.18
    æ½ŀ
    -0.18
    说æĪij
    -0.18
    POSITIVE LOGITS
    éĢĶ
    0.20
     action
    0.20
     pursued
    0.20
     direction
    0.20
    æĸ¹éĴĪ
    0.20
    棹
    0.19
     paths
    0.19
     course
    0.19
    uil
    0.19
     пÑĥÑĤи
    0.19
    Activations Density 0.030%

    No Known Activations