© 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. 2916
    Prev
    Next
    INDEX
    Explanations

    poultry layers

    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
    uche
    -0.27
     Tos
    -0.26
    è¿ĺ好
    -0.25
    饱
    -0.24
     uf
    -0.24
     Gow
    -0.23
    ..'
    -0.23
    wyn
    -0.23
     ims
    -0.22
     injecting
    -0.22
    POSITIVE LOGITS
    -like
    0.25
    Ŀ
    0.23
    ĸ
    0.23
    åĪ¶åº¦
    0.22
    éĢļçĶ¨
    0.21
    -scale
    0.21
    æľį
    0.21
    (sum
    0.20
    çļĦæł¹æľ¬
    0.20
     Suite
    0.20
    Activations Density 0.789%

    No Known Activations