© 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. 13213
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by common words

    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¸Ģæ³¢
    -0.24
    æIJŀ
    -0.23
    å±Ģ
    -0.22
    åıĤ
    -0.21
    èĦī
    -0.20
    è¯Ħ
    -0.20
    others
    -0.20
    å¼Ħ
    -0.19
    æĭĵ
    -0.19
    ev
    -0.19
    POSITIVE LOGITS
    éĻĪè¿°
    0.22
    åĵ½
    0.22
     blah
    0.21
    _ComCallableWrapper
    0.21
    è¿Ļ份
    0.20
    è¬
    0.19
    éĥijéĩį
    0.19
     bla
    0.19
    numerusform
    0.19
    cka
    0.19
    Activations Density 0.147%

    No Known Activations