© 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. 16806
    Prev
    Next
    INDEX
    Explanations

    blender, competitive, replica, tools, painte

    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
    iets
    -0.23
    iet
    -0.21
    eref
    -0.21
    çļ®
    -0.20
    åĸĦ
    -0.20
    ä»Ģä¹Īäºĭ
    -0.20
    ERE
    -0.20
    åĨ»ç»ĵ
    -0.20
    åĵį
    -0.19
    DDS
    -0.19
    POSITIVE LOGITS
    COPE
    0.19
    ntax
    0.19
    enha
    0.19
    lander
    0.19
    æµļ
    0.18
    åºĻ
    0.18
    è´¸
    0.18
    rophe
    0.17
    aison
    0.17
    åĬłä¹ĭ
    0.17
    Activations Density 0.001%

    No Known Activations