© 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. 10706
    Prev
    Next
    INDEX
    Explanations

    surface texture and features

    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
    tá
    -0.21
    èī²
    -0.21
    满满çļĦ
    -0.21
    èī²ç´ł
    -0.21
    顺
    -0.20
    çĶ¨åľ°
    -0.20
    èĶ½
    -0.20
    ä¸Ńåħ³
    -0.20
    åįĬ天
    -0.19
    éĶķ
    -0.19
    POSITIVE LOGITS
    å¾®è§Ĥ
    0.22
    表éĿ¢
    0.21
     macro
    0.21
    å®ıè§Ĥ
    0.20
     arte
    0.20
     cav
    0.20
    åŁĭ
    0.20
     created
    0.19
     unsupported
    0.19
    older
    0.18
    Activations Density 0.435%

    No Known Activations