© 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. 1846
    Prev
    Next
    INDEX
    Explanations

    case citations

    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
    URT
    -0.23
     jog
    -0.23
    /books
    -0.23
    Designer
    -0.23
    æĢĢæĬ±
    -0.23
    éĿ
    -0.22
     abandon
    -0.21
    è¡ĵ
    -0.21
    rien
    -0.21
     Cout
    -0.21
    POSITIVE LOGITS
    第ä¸ĥ
    0.30
    第ä¹Ŀ
    0.27
    第åħŃ
    0.26
    第äºĶ
    0.26
    asca
    0.25
    teenth
    0.25
    åįģä¹Ŀ
    0.24
    第åįģ
    0.24
    ä¹Ŀå¹´
    0.24
    Ñģол
    0.24
    Activations Density 0.081%

    No Known Activations