© 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. 14309
    Prev
    Next
    INDEX
    Explanations

    introduction, major, prop, vote, percentage

    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
    é¹ij
    -0.19
     Redistributions
    -0.19
    ä¸ĢæĹ¥
    -0.19
    æł²
    -0.18
    ä»¥äººä¸ºæľ¬
    -0.18
    æĶĴ
    -0.18
    é¹Ħ
    -0.18
    ESÄ°
    -0.18
    abant
    -0.18
    夫
    -0.17
    POSITIVE LOGITS
    arti
    0.21
    ISM
    0.21
     hiếm
    0.20
     вмеÑģÑĤ
    0.20
     vag
    0.20
     Slam
    0.19
    ç½ķè§ģ
    0.19
    isel
    0.19
    æ¦Ĥ
    0.18
    æĶ¶å®ĺ
    0.18
    Activations Density 0.006%

    No Known Activations