© 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. 13892
    Prev
    Next
    INDEX
    Explanations

    contrast

    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
    åĮĿ
    -0.23
    ä¸Ģ个æĺŁæľŁ
    -0.21
    unused
    -0.20
    chez
    -0.19
    -backend
    -0.19
    森
    -0.18
    æĪ¶
    -0.18
    åĪ°åľº
    -0.18
    IJľç´¢
    -0.18
    PropertyDescriptor
    -0.18
    POSITIVE LOGITS
    Spo
    0.25
     Spo
    0.21
     Babylon
    0.21
     пÑĢим
    0.20
    èĭ»
    0.20
    碣
    0.20
    缸
    0.19
    åİī害
    0.19
    å¼ºåĽ½
    0.18
    anium
    0.18
    Activations Density 0.017%

    No Known Activations