© 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. 16775
    Prev
    Next
    INDEX
    Explanations

    place names beginning with capitalized syllables

    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
    éļIJèĶ½
    -0.22
    è¯ļ
    -0.20
    RT
    -0.19
     plat
    -0.19
     intuitive
    -0.19
    çłĶ究æīĢ
    -0.18
    æĹłå£°
    -0.18
    æĢį
    -0.18
    èĻİ
    -0.18
     need
    -0.18
    POSITIVE LOGITS
    usted
    0.23
    avras
    0.19
     Battlefield
    0.19
    agini
    0.18
    _basis
    0.18
    inite
    0.18
    hattan
    0.18
    basis
    0.18
    çĨ¹
    0.17
    Æ¡i
    0.17
    Activations Density 0.110%

    No Known Activations