© 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. 15017
    Prev
    Next
    INDEX
    Explanations

    project root

    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
    à¹Ĩ
    -0.20
    -0.18
    à¹ĥà¸Ī
    -0.18
    çĸ«æĥħå½±åĵį
    -0.17
    uke
    -0.17
    èĨº
    -0.17
    thest
    -0.17
    说æĺ¯
    -0.16
    idth
    -0.16
    ANCE
    -0.16
    POSITIVE LOGITS
    ors
    0.23
    ekt
    0.19
    ive
    0.19
    iles
    0.18
    ILES
    0.17
    ype
    0.17
     Gutenberg
    0.17
    swith
    0.17
    amp
    0.17
    ives
    0.17
    Activations Density 0.075%

    No Known Activations