© 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. 943
    Prev
    Next
    INDEX
    Explanations

    coffee makers, coffee parlor

    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
    execution
    -0.27
    _execution
    -0.25
    Execution
    -0.24
    _traffic
    -0.23
    filesize
    -0.23
    æݨèįIJéĺħ读
    -0.22
     Inch
    -0.21
     Sweat
    -0.21
    夥
    -0.21
    ward
    -0.21
    POSITIVE LOGITS
     self
    0.26
    èĩªæĪij
    0.23
    /stretch
    0.23
    æ¥Ŀ
    0.23
    æłĭ
    0.23
     dép
    0.22
    iler
    0.22
    åľ¨çº¿
    0.22
     pepp
    0.21
     neg
    0.21
    Activations Density 0.001%

    No Known Activations