© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3207
    Prev
    Next
    INDEX
    Explanations

    here

    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
    Negative Logits
    ť
    -0.24
    Wolf
    -0.23
    kus
    -0.23
    IGIN
    -0.23
    azar
    -0.23
    pedia
    -0.21
    thal
    -0.21
    Äħż
    -0.21
    uzzi
    -0.21
    cou
    -0.21
    POSITIVE LOGITS
     beyond
    0.23
    abouts
    0.23
    ELS
    0.22
    aws
    0.21
     atmosphere
    0.21
     in
    0.21
    биÑĤ
    0.21
     home
    0.21
    ä¸Ģè¶Ł
    0.21
    åĮĹæĸ¹
    0.20
    Activations Density 0.022%

    No Known Activations