© 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. 1905
    Prev
    Next
    INDEX
    Explanations

    reply or be contacted

    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
    hang
    -0.26
    éĻ¡
    -0.26
    eat
    -0.25
    ä¼łç»Łäº§ä¸ļ
    -0.24
    een
    -0.23
    æľĽ
    -0.23
     societal
    -0.23
    eing
    -0.23
     piled
    -0.23
    LOSS
    -0.22
    POSITIVE LOGITS
    æĺİæĹ¥
    0.28
    -reply
    0.27
    ä¸ĭä¸ĢæŃ¥
    0.26
     Hidden
    0.24
    å°Ĩä¼ļ
    0.24
     reply
    0.23
     ÑģодеÑĢж
    0.23
     бÑĥдеÑĤ
    0.23
     Compatible
    0.23
     moderated
    0.23
    Activations Density 0.015%

    No Known Activations