© 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. 15032
    Prev
    Next
    INDEX
    Explanations

    educational course offerings

    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
    æ·±å¤Ħ
    -0.23
    è£ģåijĺ
    -0.18
    slash
    -0.18
    /Foundation
    -0.17
    è¿ľå¤Ħ
    -0.17
    ataires
    -0.17
    å±Ģéķ¿
    -0.17
    èıį
    -0.17
    讲æķħäºĭ
    -0.17
    err
    -0.16
    POSITIVE LOGITS
    åĨħ容
    0.23
    hips
    0.21
    ç»ĵæĿŁåIJİ
    0.18
    åħ§å®¹
    0.18
    æľŁéĹ´
    0.18
    vice
    0.17
    ëªħ
    0.17
    NING
    0.17
    бÑĥ
    0.17
     eyeb
    0.17
    Activations Density 0.022%

    No Known Activations