© 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. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4989
    Prev
    Next
    INDEX
    Explanations

    numerical values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\"
    -0.27
    åľ°
    -0.26
    plates
    -0.26
    Sol
    -0.25
     hindsight
    -0.25
    indsight
    -0.25
    éĨĽ
    -0.24
    å¼Ģå±Ģ
    -0.24
    dom
    -0.24
     reactions
    -0.24
    POSITIVE LOGITS
    åIJįé¢Ŀ
    0.35
    æĢ»éĩı
    0.34
    æĢ»æķ°
    0.32
     quotas
    0.29
     needed
    0.29
    份é¢Ŀ
    0.29
     quota
    0.28
    å¤ļå°ij
    0.27
    é¢Ŀ度
    0.27
    è¿ĺéľĢ
    0.27
    Activations Density 0.070%

    No Known Activations