© 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. 15123
    Prev
    Next
    INDEX
    Explanations

    director of

    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
    astic
    -0.19
    IFICATION
    -0.19
    .sky
    -0.18
    ifications
    -0.18
    æľ«
    -0.18
    èį¡
    -0.18
    verages
    -0.18
    _plate
    -0.17
    existence
    -0.17
    Reporter
    -0.17
    POSITIVE LOGITS
    åħ¼
    0.20
    èµĦæĸĻ
    0.19
    精确
    0.18
    ç»ĦæĪIJçļĦ
    0.18
    èı©
    0.18
    ç»ĦæĪIJ
    0.18
    æĪij们è¦ģ
    0.18
    åĺī
    0.18
    éĿ¢çĻ½
    0.17
    ledon
    0.17
    Activations Density 0.012%

    No Known Activations