© 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. 12925
    Prev
    Next
    INDEX
    Explanations

    proceeds will

    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
    主æµģ
    -0.21
    åĿĬ
    -0.20
    æ´Ĺ礼
    -0.19
    éĹ¯
    -0.19
    èļ¤
    -0.19
    åĬ¡å®ŀ
    -0.18
    æľīä¸Ģ天
    -0.18
    alone
    -0.18
    ç½ij约
    -0.18
    èĮĥåĽ´
    -0.17
    POSITIVE LOGITS
    åĨħç§ij
    0.21
    rush
    0.21
    iked
    0.21
    髯
    0.20
    æ¸ħè¿ľ
    0.19
    illo
    0.19
     Ãĸzel
    0.19
    æ¯ı次
    0.18
     Hayward
    0.18
    çĻ¾åĪĨä¹ĭ
    0.18
    Activations Density 0.005%

    No Known Activations