© 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. 11124
    Prev
    Next
    INDEX
    Explanations

    multi-lingual or transcribed strings

    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
    èĦĺ
    -0.23
    èĨĤ
    -0.21
    çŧ
    -0.21
    ãģĬãģĭ
    -0.20
    ys
    -0.19
    çıı
    -0.19
    ville
    -0.19
    è¿Ľåıĸ
    -0.18
    寰
    -0.18
    cart
    -0.18
    POSITIVE LOGITS
    ifu
    0.21
    daq
    0.21
     ÑĩÑĤ
    0.21
    VMLINUX
    0.20
    Ñīи
    0.20
    ’T
    0.19
    LOUR
    0.19
    PLIED
    0.19
    olland
    0.19
    ï¨
    0.18
    Activations Density 0.110%

    No Known Activations