© 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. 2384
    Prev
    Next
    INDEX
    Explanations

    growth factor receptor

    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
     Halloween
    -0.28
    èıĸ
    -0.26
     Flip
    -0.26
     Poker
    -0.24
     ACA
    -0.24
     Magick
    -0.23
     spooky
    -0.23
    igator
    -0.23
     McGr
    -0.23
     ÐĴам
    -0.23
    POSITIVE LOGITS
    mobile
    0.29
    æīĭæľº
    0.28
     Nokia
    0.27
    ä¸İä¸ŃåĽ½
    0.26
     Xperia
    0.26
     mobile
    0.25
    Bell
    0.25
    .mobile
    0.24
    icc
    0.24
     phones
    0.23
    Activations Density 0.020%

    No Known Activations