© 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. 29742
    Prev
    Next
    INDEX
    Explanations

    recycle

    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
    æĿIJ
    -0.30
    建
    -0.28
    æĿIJæĸĻ
    -0.27
     material
    -0.27
     materials
    -0.26
    åķĨåѦéĻ¢
    -0.25
    æ·Ļ
    -0.25
    æ¹¾åĮº
    -0.25
     repetition
    -0.25
    æĢĿç´¢
    -0.24
    POSITIVE LOGITS
    Skeleton
    0.29
    idency
    0.28
    trib
    0.25
    keletal
    0.25
     accur
    0.24
    eday
    0.24
    fare
    0.24
     Fay
    0.24
     jars
    0.24
    edly
    0.24
    Activations Density 0.156%

    No Known Activations