© 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. 15512
    Prev
    Next
    INDEX
    Explanations

    Benedict, Gehrig, D'Angelo, Anderson

    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§Ĵ
    -0.22
    eq
    -0.20
     ÑĢÑĥб
    -0.19
    第ä¸Ģä½į
    -0.19
     rob
    -0.18
    ale
    -0.18
    ITO
    -0.18
     ActionTypes
    -0.18
    é£İåı£
    -0.18
    piler
    -0.17
    POSITIVE LOGITS
    çĶ©
    0.20
    éĶ¢
    0.19
    æĥ¯ä¾ĭ
    0.19
    å¾®ç¬ij
    0.18
    anni
    0.18
    odi
    0.18
    å¥Ĥ
    0.18
     paired
    0.17
    ôi
    0.17
    åĽ¢è´Ń
    0.17
    Activations Density 0.001%

    No Known Activations