© 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. 12418
    Prev
    Next
    INDEX
    Explanations

    population studies and data

    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
    èĢģ人家
    -0.23
    ernet
    -0.22
    黥
    -0.18
    åľ°å¸¦
    -0.16
    bour
    -0.16
    ño
    -0.15
    ìłIJìĿĦ
    -0.15
     Tá»ķ
    -0.15
    ifiable
    -0.15
    raud
    -0.15
    POSITIVE LOGITS
    corn
    0.18
    wide
    0.17
    hood
    0.17
    hip
    0.16
    sWith
    0.16
    lect
    0.16
    ally
    0.16
    åIJijãģij
    0.16
    esco
    0.16
    etic
    0.16
    Activations Density 0.044%

    No Known Activations