© 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. 1211
    Prev
    Next
    INDEX
    Explanations

    I'm introducing myself

    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
     Belgi
    -0.28
    ertime
    -0.24
    ntax
    -0.24
    -Trump
    -0.24
     glUniform
    -0.23
    ãģľ
    -0.23
    .esp
    -0.23
    ır
    -0.23
    èĨ»
    -0.23
    ificio
    -0.23
    POSITIVE LOGITS
    åIJįåı«
    0.31
     My
    0.27
     Port
    0.27
    æĺ¯ä¸ĢåIJį
    0.26
     Amb
    0.26
     eleven
    0.26
    åIJį为
    0.26
     fellow
    0.25
     An
    0.25
     Bay
    0.25
    Activations Density 0.077%

    No Known Activations