© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 698
    Prev
    Next
    INDEX
    Explanations

    why is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    weigh
    -0.25
    rol
    -0.24
    æĭ¥
    -0.23
    ä¹ĺçĶ¨è½¦
    -0.23
    æĭ§
    -0.23
    _atom
    -0.22
     sÄĥ
    -0.22
    emap
    -0.22
    稳æŃ¥
    -0.22
    å¼Ľ
    -0.22
    POSITIVE LOGITS
     incorrectly
    0.29
     suspected
    0.28
     unethical
    0.28
     invalid
    0.28
    ä¸įå½ĵ
    0.27
    侮辱
    0.27
    è¹Ĭ
    0.27
    .partial
    0.27
     violated
    0.26
     plagiarism
    0.26
    Activations Density 0.010%

    No Known Activations