© 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. 108618
    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
     wearer
    -0.29
    eld
    -0.27
    /thumb
    -0.27
    victim
    -0.26
    Cast
    -0.26
    adar
    -0.25
    highest
    -0.25
    èĢĮåĩº
    -0.24
    æī¬å·ŀ
    -0.24
    .pdf
    -0.24
    POSITIVE LOGITS
    chs
    0.30
    大è¡Ĺ
    0.28
    unders
    0.26
    赧
    0.26
    à¸ļาย
    0.25
    åħ³
    0.25
    posix
    0.24
    essional
    0.24
    fab
    0.24
    ä¸Ńåħ³
    0.24
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.