© 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. 1537
    Prev
    Next
    INDEX
    Explanations

    genome sequencing and projects

    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
    ä¸įå½ĵ
    -0.27
    inel
    -0.24
     Favorites
    -0.22
    åĬĪ
    -0.22
    鹤
    -0.22
    reg
    -0.22
    regar
    -0.21
     requesting
    -0.21
     unsett
    -0.20
    ouble
    -0.20
    POSITIVE LOGITS
     genome
    0.30
    åŁºåĽł
    0.30
     genomes
    0.30
     Consortium
    0.29
    DNA
    0.29
    çļĦä¼Łå¤§
    0.27
     Genome
    0.26
    æĶ»åħĭ
    0.26
    人é¡ŀ
    0.26
    dna
    0.26
    Activations Density 0.080%

    No Known Activations