© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12239
    Prev
    Next
    INDEX
    Explanations

    guide and instructor

    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
    ä¹ĸä¹ĸ
    -0.20
    èļ¤
    -0.20
    è¹ī
    -0.19
    ç£ĭ
    -0.19
    ÑĥÑİÑī
    -0.18
     phoenix
    -0.17
    ouch
    -0.17
     Increment
    -0.17
    å¤Ń
    -0.17
    çĴĩ
    -0.17
    POSITIVE LOGITS
    讲解
    0.35
    å¼ķ导
    0.30
    带é¢Ĩ
    0.26
     guide
    0.26
    带éĺŁ
    0.25
     guides
    0.25
    导游
    0.25
    导读
    0.25
    æīĢæıIJä¾Ľ
    0.25
     guiding
    0.24
    Activations Density 0.015%

    No Known Activations