© 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. 16545
    Prev
    Next
    INDEX
    Explanations

    set of

    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
    å°¼äºļ
    -0.23
    åĴ«
    -0.21
    æĻ°
    -0.18
    ited
    -0.18
    ettes
    -0.17
    elmet
    -0.17
    sit
    -0.16
    æĺ¯ä¸Ģ座
    -0.16
    andest
    -0.16
    azed
    -0.15
    POSITIVE LOGITS
    ä¸Ģå¥Ĺ
    0.20
    culo
    0.19
    tle
    0.19
    tlement
    0.18
    å¿ħè¦ģçļĦ
    0.18
    mate
    0.17
    minus
    0.17
    æĪĸå¤ļ
    0.17
    icle
    0.17
    åĨħçļĦ
    0.17
    Activations Density 0.076%

    No Known Activations