© 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. 2143
    Prev
    Next
    INDEX
    Explanations

    posts, menu, visitors, dungeon

    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
    hus
    -0.25
     clipping
    -0.24
    -proof
    -0.22
     Pill
    -0.22
    BLE
    -0.22
    ä¸įåıĹ
    -0.22
     struck
    -0.22
     softened
    -0.21
     capitalist
    -0.21
     rouge
    -0.21
    POSITIVE LOGITS
     koÅĦ
    0.23
    èľ¥
    0.23
    æѤåīį
    0.22
    éĺĢéŨ
    0.22
     pore
    0.22
     amongst
    0.22
    tent
    0.22
    prite
    0.22
    ÑĥÑĢ
    0.21
    åħ¥
    0.21
    Activations Density 0.003%

    No Known Activations