© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2543
    Prev
    Next
    INDEX
    Explanations

    awards ceremonies

    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
    rail
    -0.23
    Rails
    -0.22
    éĻIJåĪ¶
    -0.22
    çģĮæºī
    -0.22
     project
    -0.22
     primitive
    -0.22
    æ´¸
    -0.22
     ostr
    -0.22
    UUID
    -0.22
    .getTag
    -0.21
    POSITIVE LOGITS
    å¹ķåIJİ
    0.36
     televised
    0.35
    çĶµè§Ĩ
    0.32
    æĴŃåĩº
    0.30
     Television
    0.30
    tv
    0.29
     television
    0.28
    ä»ĬæĻļ
    0.28
    çĺ¦èº«
    0.27
    åīįå¤ķ
    0.27
    Activations Density 0.017%

    No Known Activations