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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108834
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    oly
    -0.27
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.25
    ÑĢаниÑĨ
    -0.25
    ubic
    -0.25
    ety
    -0.24
    ä»»ä½ķå½¢å¼ı
    -0.24
     rede
    -0.24
    eric
    -0.23
    malı
    -0.23
    åħ¨æĺ¯
    -0.23
    POSITIVE LOGITS
    lander
    0.25
    lag
    0.25
    çĺª
    0.24
    inan
    0.24
     lag
    0.24
    lags
    0.24
    便
    0.24
    å·´å·´
    0.23
    ä¸ĩåħĥ以ä¸Ĭ
    0.23
    âĸ¿
    0.23
    Activations Density 0.921%

    No Known Activations

    This feature has no known activations.