© 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. 107847
    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
     Raider
    -0.27
    naz
    -0.27
    ä¼IJ
    -0.26
    plevel
    -0.26
    骤
    -0.25
    normal
    -0.25
    ulus
    -0.25
     chambers
    -0.25
    ournals
    -0.24
    pare
    -0.24
    POSITIVE LOGITS
    edImage
    0.30
    缺å¸Ń
    0.25
     tarde
    0.25
    &q
    0.24
    大éĩıçļĦ
    0.24
     Mash
    0.24
    产åĩº
    0.24
    人èĦī
    0.24
    æ¯Ķè¾ĥå¤ļ
    0.24
     postcode
    0.24
    Activations Density 0.127%

    No Known Activations

    This feature has no known activations.