© 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. 12420
    Prev
    Next
    INDEX
    Explanations

    French

    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
    ij
    -0.17
    olu
    -0.17
    arity
    -0.17
    ë§ģ
    -0.16
    ally
    -0.15
    iface
    -0.15
    traits
    -0.15
    ãĤĪãģĨãģª
    -0.15
    §
    -0.15
    изаÑĨиÑı
    -0.15
    POSITIVE LOGITS
    -speaking
    0.29
    ening
    0.20
    ify
    0.19
    burg
    0.19
    ness
    0.19
    earch
    0.19
    eners
    0.18
    berry
    0.18
    ercise
    0.18
    ìĸ´
    0.18
    Activations Density 0.026%

    No Known Activations