© 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. 11958
    Prev
    Next
    INDEX
    Explanations

    chip

    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
    iction
    -0.18
     infancy
    -0.18
    缨
    -0.17
    _closure
    -0.17
    istas
    -0.16
    âķ¯
    -0.16
    ossa
    -0.15
    atorio
    -0.15
    ;;;;
    -0.15
     afflicted
    -0.15
    POSITIVE LOGITS
    lets
    0.24
    sets
    0.21
    pery
    0.21
    lessly
    0.19
    åĦ¿
    0.18
    otle
    0.18
    ìħĭ
    0.18
    less
    0.18
    ery
    0.18
    åŃIJéĩĮ
    0.18
    Activations Density 0.009%

    No Known Activations