© 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. 2410
    Prev
    Next
    INDEX
    Explanations

    actors, characters, and names

    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
    åħ¥åĽŃ
    -0.25
     disgust
    -0.25
    åĪĥ
    -0.24
    èĻİ
    -0.24
    åıĶ
    -0.24
     Shar
    -0.24
    èľ¥
    -0.23
    Shar
    -0.23
    åĪ©
    -0.23
    æŃ¦æľ¯
    -0.23
    POSITIVE LOGITS
     knitting
    0.25
     Painting
    0.25
     Worker
    0.25
     orchestra
    0.24
     dims
    0.24
    ->__
    0.23
    帷
    0.23
    MainFrame
    0.23
    intree
    0.23
    æŁŀ
    0.22
    Activations Density 0.068%

    No Known Activations