© 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. 13955
    Prev
    Next
    INDEX
    Explanations

    original packaging or accessories

    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
    _thr
    -0.21
    羯
    -0.21
     té
    -0.20
     cái
    -0.20
    å½ĵéĢī
    -0.20
    éĢīåıĸ
    -0.19
    åı¼
    -0.19
     prison
    -0.19
     dict
    -0.18
    -master
    -0.18
    POSITIVE LOGITS
     ORIGINAL
    0.27
    åİŁä»¶
    0.26
    hợ
    0.25
    å®Įæķ´
    0.25
    å®Į好
    0.24
    ä»»ä½ķ
    0.24
    ä»»ä½ķå½¢å¼ı
    0.23
    åĮħè£ħ
    0.23
    Ñıм
    0.22
    abin
    0.22
    Activations Density 0.006%

    No Known Activations