© 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. 2622
    Prev
    Next
    INDEX
    Explanations

    zoom lens

    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
    个ä½ĵ
    -0.25
    eced
    -0.24
    æĤį
    -0.23
     ver
    -0.23
    æĬij
    -0.22
     bot
    -0.22
     grav
    -0.22
     erg
    -0.22
    antine
    -0.22
     Bot
    -0.22
    POSITIVE LOGITS
    ç®´
    0.27
    åĢį
    0.27
    å¹»
    0.27
    æĹĹèĪ°
    0.24
     duplex
    0.24
    顺便
    0.24
    æ±ľ
    0.24
    ube
    0.23
    å¼¯æĽ²
    0.23
    å³¥
    0.23
    Activations Density 0.013%

    No Known Activations