© 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. 11877
    Prev
    Next
    INDEX
    Explanations

    names starting with Bob, Alex, Robert

    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
    ç´ł
    -0.24
    循
    -0.23
    èķ´
    -0.21
    ä¼ļ
    -0.20
    åĭĺ
    -0.19
    åIJ«
    -0.19
    æİ
    -0.19
    åĶ¯ä¸ĢçļĦ
    -0.19
    åĪĴ
    -0.18
    å½¢æĪIJ
    -0.18
    POSITIVE LOGITS
     cái
    0.21
    ouched
    0.20
    chine
    0.19
    æĶ¶æķĽ
    0.19
     pedest
    0.19
    æĨ©
    0.19
    èħŃ
    0.18
    heid
    0.18
    à¸Ħา
    0.18
    Offsets
    0.18
    Activations Density 0.004%

    No Known Activations