© 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. 16548
    Prev
    Next
    INDEX
    Explanations

    frogs

    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
    orque
    -0.16
    æģ¤
    -0.15
    anno
    -0.15
    enance
    -0.15
    aire
    -0.15
    -too
    -0.15
     اÙĦÙģÙĦسطÙĬÙĨÙĬ
    -0.15
    ption
    -0.15
     Wolves
    -0.14
    æłī
    -0.14
    POSITIVE LOGITS
    swith
    0.22
    gers
    0.21
    ten
    0.19
    smith
    0.19
    lets
    0.18
    sl
    0.18
    /to
    0.18
    ging
    0.17
    äºĨä¸įå°ij
    0.17
    èĽĻ
    0.17
    Activations Density 0.011%

    No Known Activations