© 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. 1816
    Prev
    Next
    INDEX
    Explanations

    retinoid or retinoic acid

    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
    Emergency
    -0.26
    æ¿Ĵ临
    -0.24
    Authorities
    -0.23
    BODY
    -0.23
    éĶĴ
    -0.23
     communal
    -0.23
    underline
    -0.23
    æĢ§æł¼
    -0.23
    åıĹçģ¾
    -0.22
    recover
    -0.22
    POSITIVE LOGITS
    ]%
    0.26
     stead
    0.24
    æ¦Ń
    0.24
    åīįç½®
    0.24
     FO
    0.23
     intens
    0.23
    ä¸Ĭåİ»
    0.22
    åĬłæĮģ
    0.22
     oxidation
    0.21
    æĬ¤èĤ¤åĵģ
    0.21
    Activations Density 0.005%

    No Known Activations