© 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. 12623
    Prev
    Next
    INDEX
    Explanations

    unique integer values

    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
    Ñģид
    -0.19
    lint
    -0.19
     reun
    -0.19
     forg
    -0.18
     Shorts
    -0.18
    latin
    -0.18
    ffield
    -0.18
    tern
    -0.18
    жÑĥ
    -0.18
    .ping
    -0.17
    POSITIVE LOGITS
    æĸ°é¢ĸ
    0.31
    çĭ¬çī¹
    0.24
    çĭ¬ä¸ĢæĹłäºĮ
    0.23
    éģ¿åħį
    0.21
     Unique
    0.21
    æĿľç»Ŀ
    0.21
    uniq
    0.20
     Ñĥника
    0.19
     CUSTOM
    0.19
    çĭ¬ä¸Ģ
    0.19
    Activations Density 0.172%

    No Known Activations