© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107094
    Prev
    Next
    INDEX
    Explanations

    Non-English code/text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç¼Ŀ
    -0.36
    满
    -0.29
    arium
    -0.29
    viron
    -0.29
    åŀĤ
    -0.27
    ä¸įè¿ĩ
    -0.27
    åłĨ
    -0.26
    нал
    -0.26
    견
    -0.26
     molest
    -0.25
    POSITIVE LOGITS
    earer
    0.32
    èĪī
    0.27
    atham
    0.27
    館
    0.26
    èĭĮ
    0.26
     Ember
    0.25
    ãĤīãģļ
    0.25
    ettel
    0.25
    ersions
    0.25
    æĿĵ
    0.25
    Activations Density 0.106%

    No Known Activations