© 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. 15451
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tram
    -0.20
    ä»ģ
    -0.19
    ç»IJ
    -0.18
    eren
    -0.18
    mise
    -0.18
    åľ¨æĦı
    -0.18
    leur
    -0.17
    缮
    -0.17
    cuts
    -0.17
    åĴİ
    -0.17
    POSITIVE LOGITS
     perch
    0.20
    soever
    0.18
    çĪ·
    0.18
    峦
    0.18
    ucci
    0.18
    ãģĭãģ¤
    0.17
    æįħ
    0.17
    楼
    0.17
    gia
    0.17
    dro
    0.17
    Activations Density 0.000%

    No Known Activations