© 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. 884
    Prev
    Next
    INDEX
    Explanations

    standard deviation or state information

    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
     workflows
    -0.25
    åºļ
    -0.24
    ijľ
    -0.24
     deleg
    -0.24
    tü
    -0.23
     spring
    -0.23
    éķ¶
    -0.23
     Spring
    -0.23
     trab
    -0.23
    è¯ķè¯ķ
    -0.23
    POSITIVE LOGITS
    åĪĨåĪ«ä¸º
    0.35
    åĪĨåĪ«æĺ¯
    0.26
    (_,
    0.25
    )=(
    0.23
    :X
    0.23
    anan
    0.22
     Norris
    0.22
    .tail
    0.22
    Spoiler
    0.22
     numerator
    0.22
    Activations Density 0.064%

    No Known Activations