© 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. 10709
    Prev
    Next
    INDEX
    Explanations

    technical terms or phrases

    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
    饥饿
    -0.20
    _SAN
    -0.19
    缧
    -0.19
    çī
    -0.19
    缸éĢļ
    -0.19
    åºł
    -0.19
     bol
    -0.18
    usercontent
    -0.18
    åīIJ
    -0.18
    å¹³åĿĩæ°´å¹³
    -0.18
    POSITIVE LOGITS
    èī¯æĢ§
    0.21
    ToFront
    0.21
    TRS
    0.20
    lund
    0.20
    TRACT
    0.20
    éĻĦè¿ij
    0.20
     hạ
    0.19
    åıįé¦Ī
    0.18
    LocalizedString
    0.18
    秣æĪ¿
    0.18
    Activations Density 0.012%

    No Known Activations