© 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. 107862
    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
    ç½ij讯
    -0.31
    overe
    -0.29
    ldr
    -0.27
    onte
    -0.27
     RIGHTS
    -0.27
    ä¸Ģç»ı
    -0.26
    æ°´å¹³
    -0.26
    imps
    -0.25
    Sci
    -0.25
    chunks
    -0.25
    POSITIVE LOGITS
     properly
    0.25
     perk
    0.24
    pair
    0.24
     unfolding
    0.23
     pair
    0.23
    缸è¯Ĩ
    0.23
    uzu
    0.23
     autom
    0.23
     prefer
    0.23
    _embed
    0.23
    Activations Density 0.839%

    No Known Activations

    This feature has no known activations.