© 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. 29973
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    uhn
    -0.31
    issement
    -0.29
    ousedown
    -0.27
    ær
    -0.27
    locking
    -0.26
    顺åºĶ
    -0.26
    few
    -0.25
    èĩ¾
    -0.25
    FileStream
    -0.25
    mts
    -0.25
    POSITIVE LOGITS
    Compar
    0.29
     comparative
    0.27
    ç»ķ
    0.27
    æĢĢçĿĢ
    0.26
    mach
    0.26
     arch
    0.26
    Reach
    0.25
    incy
    0.25
     Depos
    0.25
     tor
    0.25
    Activations Density 21.465%

    No Known Activations

    This feature has no known activations.