© 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. 16828
    Prev
    Next
    INDEX
    Explanations

    genetic markers and codes

    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
    Compose
    -0.19
    ahi
    -0.19
    éĹ³
    -0.19
    é«ĺæķĪçļĦ
    -0.19
     excer
    -0.19
     Tanks
    -0.18
    åĮĹè·¯
    -0.18
    éĵİ
    -0.18
    eria
    -0.18
    ç¥ŀéĢļ
    -0.18
    POSITIVE LOGITS
    0.23
    ï¸ı
    0.21
    wards
    0.20
    ↵
    0.20
    /from
    0.20
     (
    0.19
    /of
    0.19
     which
    0.19
    anners
    0.19
    /global
    0.19
    Activations Density 0.026%

    No Known Activations