© 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. 107325
    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
    WAR
    -0.27
    ings
    -0.25
    itu
    -0.24
    ãĥIJãĥĥãĤ¯
    -0.23
    string
    -0.23
    çĿĢ
    -0.23
    By
    -0.23
    å»ī
    -0.22
    emon
    -0.22
    embed
    -0.22
    POSITIVE LOGITS
    æ·¼
    0.25
    MLE
    0.24
    aceous
    0.24
    purpose
    0.24
     Damen
    0.23
    lessly
    0.23
    大éĻĨ
    0.23
    daÄŁ
    0.23
     Thom
    0.23
    åĨ¥
    0.23
    Activations Density 3.628%

    No Known Activations

    This feature has no known activations.