© 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. 2998
    Prev
    Next
    INDEX
    Explanations

    long-term care

    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
    æ¦ĥ
    -0.27
     referencing
    -0.26
     Displays
    -0.26
     flashback
    -0.26
    æ¾Ľ
    -0.25
     displayed
    -0.25
     incorporating
    -0.25
     visuals
    -0.25
    å¨ĵ
    -0.25
    æīĭåĬ¿
    -0.24
    POSITIVE LOGITS
    èĩªæĦ¿
    0.30
    ç©·
    0.30
     billig
    0.29
    èĩªçIJĨ
    0.29
     harms
    0.29
     consenting
    0.29
    ç»ıæµİ
    0.28
    çĶŁçĹħ
    0.28
    çĶŁäº§çĶŁæ´»
    0.27
     economically
    0.27
    Activations Density 0.029%

    No Known Activations