© 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. 15102
    Prev
    Next
    INDEX
    Explanations

    check it out

    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
    éli
    -0.18
    /by
    -0.17
    .digital
    -0.17
    flake
    -0.15
    essor
    -0.15
    isk
    -0.15
    ³
    -0.15
    æ»Ĥ
    -0.15
    -kind
    -0.14
    åIJĮå¿Ĺ
    -0.14
    POSITIVE LOGITS
    äºĨä¸Ģä¸ĭ
    0.25
    ä¸Ģä¸ĭ
    0.23
    æĺ¯åIJ¦æľī
    0.22
    ered
    0.22
    icles
    0.20
    æł¸å®ŀ
    0.20
    OrCreate
    0.19
    rooms
    0.19
    ìĤ¬íķŃ
    0.18
     WHETHER
    0.18
    Activations Density 0.065%

    No Known Activations