© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 165
    Prev
    Next
    INDEX
    Explanations

    decimal point followed by numbers

    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
    edBy
    -0.29
    ANCE
    -0.20
    (pl
    -0.19
     /*!
    -0.19
    riers
    -0.19
    OURS
    -0.19
    AndView
    -0.19
    (Of
    -0.19
    --[
    -0.18
     опиÑģание
    -0.18
    POSITIVE LOGITS
    åįĬ天
    0.23
    -inch
    0.22
    å®īåħ¨äºĭæķħ
    0.21
    åīįæīĢ
    0.21
    :///
    0.21
    -rated
    0.21
    åįģä¸īäºĶ
    0.21
    æĬķèµĦé¢Ŀ
    0.20
    éĢŁ
    0.20
    ç£ķ
    0.20
    Activations Density 0.011%

    No Known Activations