© 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. 16001
    Prev
    Next
    INDEX
    Explanations

    combine, enter, scan, render, request

    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
    交
    -0.19
    èijŃ
    -0.19
    æĥ¯
    -0.18
    æ°Ķ
    -0.18
    æĶ¯
    -0.18
    声
    -0.18
    追
    -0.18
    less
    -0.18
    ment
    -0.18
    åĢĻ
    -0.18
    POSITIVE LOGITS
    ä¸Ģå°ģä¿¡
    0.22
    第ä¸Ģæī¹
    0.22
    åĬłå¿«åıijå±ķ
    0.22
    缸éĹľæľįåĭĻ
    0.20
    对人ä½ĵ
    0.19
    åIJĦæł·
    0.19
    æİĴåIJį第
    0.19
    annie
    0.18
    æīĢéľĢçļĦ
    0.18
    æīĢéľĢè¦ģçļĦ
    0.18
    Activations Density 0.119%

    No Known Activations