© 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. 648
    Prev
    Next
    INDEX
    Explanations

    an SSLan MITan email

    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
    s
    -0.28
    ëĬĶ
    -0.26
    iness
    -0.26
    less
    -0.25
    åľ¨
    -0.24
    åľ¨çİ°åľº
    -0.24
    lessness
    -0.24
    e
    -0.24
    gether
    -0.23
    人éĢī
    -0.23
    POSITIVE LOGITS
    tributes
    0.31
     slight
    0.28
    tra
    0.28
    tribute
    0.27
    /an
    0.26
    theros
    0.26
    å°ıå°ıçļĦ
    0.25
     refined
    0.24
     simplified
    0.24
     large
    0.24
    Activations Density 0.345%

    No Known Activations