© 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. 9-TRANSCODER-HP
    7. 29580
    Prev
    Next
    INDEX
    Explanations

    lengthy text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whereas
    -0.27
     Jays
    -0.26
    ital
    -0.24
    arLayout
    -0.24
    è°ħ
    -0.24
    _migration
    -0.24
    Visited
    -0.24
     order
    -0.24
     Order
    -0.24
    amer
    -0.23
    POSITIVE LOGITS
    veled
    0.31
    osed
    0.28
    ences
    0.27
    åĮĸçļĦ
    0.27
    erve
    0.26
    én
    0.25
     ФедеÑĢ
    0.25
     Scheme
    0.24
     vars
    0.24
    Reflection
    0.24
    Activations Density 1.171%

    No Known Activations