© 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. 12725
    Prev
    Next
    INDEX
    Explanations

    methods following object instantiation

    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
    iếc
    -0.21
    edia
    -0.19
    å¹´ä¹ĭ
    -0.18
    使ä¹ĭ
    -0.18
     Guaranteed
    -0.18
     Pens
    -0.18
     Hover
    -0.18
     personally
    -0.18
    çĪ±
    -0.17
    ports
    -0.17
    POSITIVE LOGITS
    .set
    0.21
    иÑĤеÑĤ
    0.20
    à¸Ļà¹Ĥย
    0.20
    以èī²
    0.19
    å¼Ģåľº
    0.18
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    0.18
    çĿĢçľ¼
    0.18
    åįł
    0.18
    blers
    0.17
    å¸ĪèĮĥ
    0.17
    Activations Density 0.344%

    No Known Activations