© 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. 2687
    Prev
    Next
    INDEX
    Explanations

    Not followed by exceptions or elaborations

    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
     realmente
    -0.21
    /vector
    -0.20
     également
    -0.20
    hoot
    -0.20
    åıĹåĪ°å½±åĵį
    -0.20
    人们对
    -0.19
    /lic
    -0.19
    HOME
    -0.19
    WARN
    -0.19
    æĢİä¹ĪåĬŀ
    -0.19
    POSITIVE LOGITS
    ting
    0.33
    çĦ¶æĺ¯
    0.28
    ransition
    0.27
    withstanding
    0.27
    tingham
    0.26
    åı¯æĥľ
    0.26
    ness
    0.25
    ummy
    0.24
    à¹Ģà¸īà¸ŀาะ
    0.24
    ional
    0.24
    Activations Density 0.068%

    No Known Activations