© 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. 12696
    Prev
    Next
    INDEX
    Explanations

    objective or problem statement

    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
    带ä¸Ĭ
    -0.20
    amin
    -0.20
    éľĦ
    -0.20
    patial
    -0.19
    çľģåĨħ
    -0.18
    å·ī
    -0.18
    ä¸ĢæŃ¥æŃ¥
    -0.18
     footwear
    -0.18
    itan
    -0.18
    æĪķ
    -0.17
    POSITIVE LOGITS
    ReadStream
    0.21
    çĪ±ç¾İ
    0.20
     aver
    0.20
    iets
    0.20
    çĶ²æĸ¹
    0.19
    å»ī
    0.19
    ÑĤаÑĢ
    0.18
    éĴ®
    0.18
    èĬĤ
    0.18
     Econom
    0.18
    Activations Density 0.094%

    No Known Activations