© 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. 16805
    Prev
    Next
    INDEX
    Explanations

    family and friends

    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
    æIJ
    -0.22
    :start
    -0.21
    orer
    -0.21
    ä¿¡ç®±
    -0.20
    ouch
    -0.20
    comed
    -0.19
    åıij声
    -0.19
    夺åıĸ
    -0.19
    umper
    -0.19
     underlying
    -0.19
    POSITIVE LOGITS
    ä¸Ģè¡Į
    0.29
    éĻªåIJĮ
    0.28
    游çİ©
    0.25
    åIJĮè¡Į
    0.25
    æĹħ游
    0.24
    游è§Ī
    0.24
    æĹħè¡Į
    0.24
    èĩªé©¾
    0.24
    ä¸ĢåIJĮ
    0.23
    ä¸Ģç»Ħ
    0.23
    Activations Density 0.062%

    No Known Activations