© 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. 1268
    Prev
    Next
    INDEX
    Explanations

    places and leagues

    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
    arpa
    -0.27
     Trustees
    -0.26
    Toolbar
    -0.25
     aggrav
    -0.25
    ä¸ĸçķĮç»ıæµİ
    -0.25
     sensual
    -0.24
    ç¾İåĽ½æĢ»ç»Ł
    -0.23
    _DICT
    -0.23
    ç©¿è¡£
    -0.23
    /book
    -0.23
    POSITIVE LOGITS
    åľ°åĮº
    0.36
    èµĽåĮº
    0.35
    æľ¬åľŁ
    0.33
     region
    0.31
    åľ°åĮºçļĦ
    0.30
    åħĦå¼Ł
    0.28
     tournament
    0.28
    éĢīæīĭ
    0.28
    èģĶèµĽ
    0.27
    éĶ¦æłĩèµĽ
    0.27
    Activations Density 0.117%

    No Known Activations