© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1284
    Prev
    Next
    INDEX
    Explanations

    presidential cycling tour

    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
     Neon
    -0.28
     karÅŁ
    -0.28
    Lorem
    -0.28
     Burnett
    -0.25
    locator
    -0.24
     Teens
    -0.24
    çļĦ女åŃ©
    -0.24
    ä¸ºçĽ®çļĦ
    -0.24
     ciclo
    -0.24
    大大å°ıå°ı
    -0.24
    POSITIVE LOGITS
     publicly
    0.41
    åħ¬å¼Ģ
    0.38
     presidential
    0.37
     public
    0.35
     himself
    0.35
    åĨħéĺģ
    0.35
    çĻ½å®«
    0.33
    æĶ¿æ²»
    0.32
    çļĦæĶ¿æ²»
    0.32
    è§Ĩå¯Ł
    0.32
    Activations Density 0.125%

    No Known Activations