© 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. 16604
    Prev
    Next
    INDEX
    Explanations

    I'm / it's contractions

    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
    åĹIJ
    -0.27
    æ®Ĭ
    -0.22
    çĤī
    -0.19
    æ±ł
    -0.18
    çĪµå£«
    -0.18
     tow
    -0.18
    (*(
    -0.18
    à¦Ń
    -0.18
    åľ¨åĨħçļĦ
    -0.17
    èĢĮéĿŀ
    -0.17
    POSITIVE LOGITS
    à¹Ĩ
    0.24
    们
    0.24
    åĢij
    0.23
    ä¹Ī
    0.23
    çĦ¶æĺ¯
    0.22
    imately
    0.22
    å¤Ł
    0.21
    ä¸ªå·¥ä½ľ
    0.21
    maal
    0.21
    ä¹İ
    0.21
    Activations Density 0.267%

    No Known Activations