© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 822
    Prev
    Next
    INDEX
    Explanations

    mighty or majestic descriptions

    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
    abouts
    -0.20
    iline
    -0.20
    inator
    -0.19
    æľ¦
    -0.19
     Gord
    -0.19
    opoly
    -0.19
    ষ
    -0.19
    iton
    -0.19
    hop
    -0.19
    laps
    -0.19
    POSITIVE LOGITS
     strides
    0.26
    壮è§Ĥ
    0.23
     roar
    0.22
     mẽ
    0.21
     bulk
    0.21
    ä¹ĭåĬ¿
    0.21
    æ°ĶåĬ¿
    0.21
    åŁºçŁ³
    0.20
    大çļĦ
    0.20
     bulls
    0.20
    Activations Density 0.016%

    No Known Activations