© 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. 117
    Prev
    Next
    INDEX
    Explanations

    locations followed by "of"

    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
    åĨľå®¶
    -0.23
    DBC
    -0.23
    æ°ijæĹıæĸĩåĮĸ
    -0.23
    é«ĺéĢŁåħ¬è·¯
    -0.22
    èijĨ
    -0.22
    åľ°å¸¦
    -0.22
    å¦Ħ
    -0.21
    çĺģ
    -0.21
    culo
    -0.21
    ä¸į平衡
    -0.21
    POSITIVE LOGITS
    _limits
    0.26
     split
    0.24
    ships
    0.24
    主æīĵ
    0.24
     Hastings
    0.23
    å¨ĺ
    0.22
    entine
    0.22
    .Direction
    0.22
     Locate
    0.22
     Bachelor
    0.22
    Activations Density 0.055%

    No Known Activations