© 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. 2145
    Prev
    Next
    INDEX
    Explanations

    automobile repair service

    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
    çĥŃ带
    -0.28
     ascent
    -0.25
    æĹºçĽĽ
    -0.24
    æĹħ游å±Ģ
    -0.23
    çĶ³è´Ń
    -0.23
    annual
    -0.23
    红èĸ¯
    -0.22
     anth
    -0.22
     tropical
    -0.22
    èĦĪ
    -0.22
    POSITIVE LOGITS
    ä¿®å¤į
    0.33
    å¤įå·¥
    0.30
     Restore
    0.29
     restores
    0.29
     restore
    0.29
    èµĶåģ¿
    0.28
     restoration
    0.28
    车主
    0.28
    restore
    0.28
    damage
    0.28
    Activations Density 0.020%

    No Known Activations