© 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. 14154
    Prev
    Next
    INDEX
    Explanations

    lane contexts

    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
    ness
    -0.21
    ÑģÑı
    -0.20
    sWith
    -0.19
    nya
    -0.18
    èĻı
    -0.18
    æĶĺ
    -0.17
    ilian
    -0.17
    è¿ĻåĦ¿
    -0.16
    ations
    -0.16
    禳
    -0.16
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.23
    åĨħçļĦ
    0.19
    人士
    0.19
    好
    0.17
    ways
    0.16
    boat
    0.15
    lettes
    0.15
    alysis
    0.15
    book
    0.15
    pipes
    0.15
    Activations Density 0.011%

    No Known Activations