© 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. 11792
    Prev
    Next
    INDEX
    Explanations

    Red Hat

    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
    otte
    -0.19
    仪
    -0.19
     CONTRIBUTORS
    -0.19
    Ñĩ
    -0.18
    lep
    -0.18
    HCI
    -0.17
     Lah
    -0.17
    HDR
    -0.17
    åį¤
    -0.17
    çķĶ
    -0.17
    POSITIVE LOGITS
     ®
    0.19
    lessly
    0.18
    quires
    0.18
    TP
    0.18
    iges
    0.17
    clidean
    0.17
    èļĵ
    0.17
     circumcision
    0.17
    .Modules
    0.17
    ®
    0.17
    Activations Density 0.004%

    No Known Activations