© 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. 1308
    Prev
    Next
    INDEX
    Explanations

    conjunctions followed by concepts

    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
    uters
    -0.26
    ably
    -0.26
    è¿Ļæł·åģļ
    -0.26
    è¿Ļä¹Īåģļ
    -0.25
    _DU
    -0.25
    ç´¯äºĨ
    -0.23
    åĻ¨
    -0.23
    éģĩä¸Ĭ
    -0.23
    æĸ°çļĦ
    -0.22
    æĴĩ
    -0.22
    POSITIVE LOGITS
     of
    0.40
     của
    0.39
    à¸Ĥà¸Ńà¸ĩ
    0.36
     entirety
    0.34
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.29
     workings
    0.25
    /or
    0.24
     ofs
    0.24
     importance
    0.24
    OfFile
    0.24
    Activations Density 0.130%

    No Known Activations