© 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. 16173
    Prev
    Next
    INDEX
    Explanations

    classes and lessons

    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
    缨
    -0.22
     вÑĭвод
    -0.21
    涮
    -0.20
    太大
    -0.20
    Spi
    -0.20
    åĬŃ
    -0.19
    è¡Įäºĭ
    -0.19
    UTH
    -0.19
    è§ŀ
    -0.19
    'gc
    -0.18
    POSITIVE LOGITS
    æ¯ıåij¨
    0.28
     sessions
    0.26
    Regular
    0.25
    regular
    0.25
    sessions
    0.24
     Regular
    0.24
    _regular
    0.24
     regular
    0.24
     session
    0.23
    priv
    0.23
    Activations Density 0.069%

    No Known Activations