© 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. 15211
    Prev
    Next
    INDEX
    Explanations

    superintendent or inspector titles

    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
    樽
    -0.18
    äºĨä»ĸçļĦ
    -0.18
    ings
    -0.18
    tÃŃ
    -0.16
     tá»ij
    -0.16
    foot
    -0.16
    fully
    -0.15
    éĨħ
    -0.15
     rÃłng
    -0.15
    ÑĦиз
    -0.15
    POSITIVE LOGITS
    ebra
    0.23
    cies
    0.20
    ean
    0.19
    orry
    0.19
    åĬ©çIJĨ
    0.18
    表æī¬
    0.18
    åħ¥å¸Ĥ
    0.17
    ees
    0.17
    al
    0.17
    pread
    0.17
    Activations Density 0.004%

    No Known Activations