© 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. 13924
    Prev
    Next
    INDEX
    Explanations

    IP addresses and ports

    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
    èĦļ
    -0.19
    ç¾ŀ
    -0.19
    éĵĮ
    -0.18
    IZE
    -0.18
    vox
    -0.17
    viar
    -0.17
    cott
    -0.17
     bodies
    -0.17
    imulator
    -0.17
    oden
    -0.17
    POSITIVE LOGITS
    å¾·æĭī
    0.22
    éĨ´
    0.19
    ä¸ĢæĹı
    0.18
    claimed
    0.18
    人å±ħçݯå¢ĥ
    0.18
    tered
    0.17
    ÙĪÙĦÙĬ
    0.17
    евиÑĩ
    0.17
    sonian
    0.17
    chn
    0.17
    Activations Density 0.004%

    No Known Activations