© 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. 11443
    Prev
    Next
    INDEX
    Explanations

    light and dark

    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
    ieder
    -0.23
    aal
    -0.19
    orman
    -0.19
    ç¼Ł
    -0.18
    è¦ģä¹Ī
    -0.18
    èĢĮåİ»
    -0.18
     Keystone
    -0.18
    å¹ķåIJİ
    -0.17
    _PG
    -0.17
    _VIS
    -0.17
    POSITIVE LOGITS
    åĬ³
    0.23
    å¡į
    0.22
    ä»Ĺ
    0.22
     nau
    0.21
    橹
    0.20
    éĽĨ
    0.19
    ç§ijçłĶéĻ¢æīĢ
    0.19
    /Instruction
    0.18
    utory
    0.18
    _PCI
    0.18
    Activations Density 0.045%

    No Known Activations