© 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. 15368
    Prev
    Next
    INDEX
    Explanations

    Marvel media

    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
    ä½łçľĭ
    -0.19
    irá
    -0.17
    éĻ¤éĿŀ
    -0.17
    ĺ认
    -0.17
    ắm
    -0.16
    spiel
    -0.16
    roller
    -0.16
    IRE
    -0.16
    rophy
    -0.15
    ercul
    -0.15
    POSITIVE LOGITS
    ous
    0.27
    ously
    0.25
    椽
    0.18
    åĮı
    0.17
    thic
    0.17
    ably
    0.17
    ity
    0.17
    ä¸Ģä¸ĭ
    0.17
    ender
    0.17
    izar
    0.17
    Activations Density 0.005%

    No Known Activations