© 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. 2287
    Prev
    Next
    INDEX
    Explanations

    how to, I am, any suggestions

    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
    icc
    -0.22
    veloper
    -0.22
    pot
    -0.22
     mixed
    -0.21
     contrib
    -0.21
    æĢ§
    -0.21
    dao
    -0.20
    ductive
    -0.20
    feas
    -0.20
    pped
    -0.20
    POSITIVE LOGITS
     firstly
    0.25
     Firstly
    0.25
    åħĪæĺ¯
    0.25
    oldt
    0.24
    é¦ĸåħĪæĺ¯
    0.23
    èĩĬ
    0.23
    辦æ³ķ
    0.23
    çļĦåĬŀæ³ķ
    0.21
    é¦ĸåħĪè¦ģ
    0.21
    åĨ°ç®±
    0.21
    Activations Density 0.142%

    No Known Activations