© 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. 16325
    Prev
    Next
    INDEX
    Explanations

    judging importance or worth

    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
    ä¿Ŀéļľ
    -0.20
    prev
    -0.20
    æ±Łå±±
    -0.20
    alık
    -0.18
    åĢĴéľī
    -0.18
     mükem
    -0.18
     вой
    -0.17
    ë§ŀ
    -0.17
     [~,
    -0.17
    Explicit
    -0.17
    POSITIVE LOGITS
    çľĭä¸Ģä¸ĭ
    0.32
    äºĨ解ä¸Ģä¸ĭ
    0.27
     ourselves
    0.25
    çľĭçľĭ
    0.25
    èĢĥèĻij
    0.24
    èĢĥå¯Ł
    0.24
    åĪĨæŀIJ
    0.24
    åİ»çľĭçľĭ
    0.23
    æ³¼
    0.23
    çIJĨ解
    0.23
    Activations Density 0.106%

    No Known Activations