© 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. 14793
    Prev
    Next
    INDEX
    Explanations

    some of the

    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
    è¿Ļä¸ĢçĤ¹
    -0.22
     something
    -0.22
     anything
    -0.21
    à¸ĵ
    -0.21
    éĻ¤æѤä¹ĭå¤ĸ
    -0.20
    æŁIJç§į
    -0.20
    æľī大éĩıçļĦ
    -0.19
    æľīä»»ä½ķ
    -0.19
    è¿ĻçĤ¹
    -0.19
     lots
    -0.18
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.19
    ç¦ıå¾·
    0.19
    otted
    0.19
    entication
    0.17
    éĽī
    0.17
    iras
    0.17
    .mx
    0.17
    常çĶ¨çļĦ
    0.17
    å°ª
    0.17
    imated
    0.16
    Activations Density 0.047%

    No Known Activations