© 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. 15163
    Prev
    Next
    INDEX
    Explanations

    visit followed by location or url

    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
    sı
    -0.19
    æĸ¯
    -0.18
    sen
    -0.18
    eration
    -0.18
    ish
    -0.17
    çīĩ
    -0.17
    éĻIJ度
    -0.17
    raft
    -0.17
    ç§
    -0.17
    iel
    -0.17
    POSITIVE LOGITS
    ãĤĤãģĨ
    0.21
    ä¸Ģè¶Ł
    0.17
    ãģĻãģIJãģ«
    0.17
    OrCreate
    0.17
    ABLE
    0.17
    nearest
    0.17
    '))->
    0.16
    .libs
    0.16
    èµĦäº§è´ŁåĢº
    0.16
    ioned
    0.16
    Activations Density 0.018%

    No Known Activations