© 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. 1421
    Prev
    Next
    INDEX
    Explanations

    Stat followed by i stical or i cs

    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
    -quarters
    -0.22
    ÑģÑĤÑĢ
    -0.20
    YLE
    -0.20
    ered
    -0.19
    à¨Ĩ
    -0.19
    sad
    -0.18
    audi
    -0.18
    èħ¹éĥ¨
    -0.18
    åĩºä¼Ĺ
    -0.18
    çĶŁåij½åij¨æľŁ
    -0.18
    POSITIVE LOGITS
    istical
    0.32
    istic
    0.27
    emachine
    0.25
    ISTICS
    0.25
    ting
    0.23
    sWith
    0.23
    itics
    0.23
    manship
    0.22
    istically
    0.22
    igraphy
    0.22
    Activations Density 0.023%

    No Known Activations