© 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. 11871
    Prev
    Next
    INDEX
    Explanations

    international bestsellers, experience, characters

    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
    .rgb
    -0.22
    ullo
    -0.19
    ELLOW
    -0.19
    çĻ£
    -0.18
    egra
    -0.18
    ispers
    -0.18
    buzz
    -0.18
    imity
    -0.17
    ä¸Ĭä¸ĭ游
    -0.17
    á»ĩ
    -0.17
    POSITIVE LOGITS
    çİ°å®ŀçĶŁæ´»
    0.30
    çİ°å®ŀä¸Ń
    0.24
     characters
    0.22
    åİŁèijĹ
    0.21
    åıĻ
    0.21
    çİ°å®ŀ
    0.21
    èĻļæŀĦ
    0.20
    çļĦ羣å®ŀ
    0.20
     simulated
    0.20
     plot
    0.20
    Activations Density 0.337%

    No Known Activations