© 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. 2402
    Prev
    Next
    INDEX
    Explanations

    notes and footnotes

    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
     Fre
    -0.26
    æ´»åĬ¨ä¸Ń
    -0.24
     Norm
    -0.24
    ioned
    -0.22
    event
    -0.21
    ä¸įåIJĪéĢĤ
    -0.21
    teacher
    -0.21
    HEET
    -0.21
    沿éĢĶ
    -0.21
    icas
    -0.20
    POSITIVE LOGITS
    è¿Ļä¸įæĺ¯
    0.24
    è¿Ļæĺ¯
    0.23
     aff
    0.23
    Attached
    0.23
    æĺ§
    0.22
    èĥĮåIJİçļĦ
    0.22
    >xpath
    0.22
    æĭĵ
    0.22
    cion
    0.22
    _plain
    0.22
    Activations Density 0.010%

    No Known Activations