© 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. 12640
    Prev
    Next
    INDEX
    Explanations

    Achilles tendon, Allegheny, Allegations

    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
    maids
    -0.19
    piece
    -0.18
    æİĢèµ·
    -0.18
     Valid
    -0.17
    ured
    -0.17
     Universal
    -0.16
    æĶ¿æĿĥ
    -0.16
    å®ŀçİ°äºĨ
    -0.16
     Ske
    -0.16
    manship
    -0.16
    POSITIVE LOGITS
    åįļçī©
    0.22
    eds
    0.19
    inox
    0.17
    该éĻ¢
    0.17
    Åijs
    0.17
    å°±éľĢè¦ģ
    0.17
    ohl
    0.17
    odont
    0.16
    iot
    0.16
    atas
    0.16
    Activations Density 0.004%

    No Known Activations