© 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. 10838
    Prev
    Next
    INDEX
    Explanations

    culinary or literary journals

    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
    /fs
    -0.17
    ront
    -0.17
    åİĨ代
    -0.16
    é«Ģ
    -0.16
    åĨħç½®
    -0.16
    geber
    -0.16
    OrCreate
    -0.15
    itan
    -0.15
    imas
    -0.15
    æ¯ĸ
    -0.15
    POSITIVE LOGITS
    tron
    0.21
    ÙĬÙĬÙĨ
    0.19
    ä¹ĭäºĭ
    0.18
    hil
    0.17
    uart
    0.17
    ultipart
    0.17
    quipe
    0.17
    trans
    0.17
    Ŀ
    0.16
    isphere
    0.16
    Activations Density 0.004%

    No Known Activations