© 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. 13345
    Prev
    Next
    INDEX
    Explanations

    including or even

    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
    æĹłè®ºå¦Ĥä½ķ
    -0.22
    碣
    -0.21
    .buf
    -0.20
    åĩłåIJį
    -0.19
    á»°
    -0.19
    è¾ĥ大
    -0.19
     nevertheless
    -0.19
    åĩłä½į
    -0.18
     Bros
    -0.18
    .twig
    -0.18
    POSITIVE LOGITS
    éĤ£äºĽ
    0.31
     those
    0.28
     ones
    0.24
    those
    0.22
    æľĢéĩįè¦ģçļĦ
    0.22
     Those
    0.21
    è¿Ļæł·æīįèĥ½
    0.20
    æĪijèĩªå·±
    0.20
     gran
    0.20
    ties
    0.20
    Activations Density 0.055%

    No Known Activations