© 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. 52
    Prev
    Next
    INDEX
    Explanations

    domestic violence abuse

    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
    ingly
    -0.26
    å½ĵåľ°æĶ¿åºľ
    -0.22
    fully
    -0.22
    æł·çļĦ
    -0.20
    lobal
    -0.19
    rost
    -0.19
    åĽ½åĨħå¤ĸ
    -0.19
    å½ĵåľ°çļĦ
    -0.19
    ä¸ĸ人
    -0.18
     successive
    -0.18
    POSITIVE LOGITS
    ity
    0.42
    çĶŁäº§æĢ»åĢ¼
    0.39
    ated
    0.39
    åĮĸçļĦ
    0.32
    ized
    0.32
    ation
    0.31
    ization
    0.30
    /int
    0.29
    ATED
    0.28
    izing
    0.28
    Activations Density 0.014%

    No Known Activations