© 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. 1909
    Prev
    Next
    INDEX
    Explanations

    words following article or growth

    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
    tea
    -0.22
    Sin
    -0.21
     adapt
    -0.21
    顺åºĶ
    -0.21
    Owners
    -0.21
    akter
    -0.21
    itial
    -0.20
    PW
    -0.20
    ptic
    -0.20
    BufferSize
    -0.20
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.67
     only
    0.43
    åIJĹ
    0.39
    ãģĭãģ©ãģĨãģĭ
    0.39
     but
    0.38
    ä½Ĩ
    0.37
    /not
    0.37
    only
    0.36
     albeit
    0.35
     neither
    0.34
    Activations Density 0.566%

    No Known Activations