© 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. 15449
    Prev
    Next
    INDEX
    Explanations

    video converters, audio converters, PDF readers, MDB merge, Partition manager

    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
    移åĬ¨ç«¯
    -0.20
    nas
    -0.19
    nock
    -0.19
    çĬĬ
    -0.18
    Ñıм
    -0.18
    广éĺĶçļĦ
    -0.18
    edx
    -0.18
     carc
    -0.17
    apan
    -0.17
    åĵĢ
    -0.17
    POSITIVE LOGITS
    åĪ«äºº
    0.20
    çĸijéļ¾
    0.20
    èĥ¶
    0.19
    occup
    0.19
    个æĢ§åĮĸ
    0.19
    ç¾İåĮĸ
    0.19
    大åħ¨
    0.19
    CanBeConverted
    0.19
     generator
    0.18
    è½»æĿ¾
    0.18
    Activations Density 0.151%

    No Known Activations