© 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. 29675
    Prev
    Next
    INDEX
    Explanations

    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
     channel
    -0.28
    leigh
    -0.26
     nest
    -0.26
    iset
    -0.26
    ernel
    -0.25
     gubern
    -0.25
    agli
    -0.25
    ($__
    -0.25
     dice
    -0.24
     tess
    -0.24
    POSITIVE LOGITS
    ä¸ĢçĤ¹åĦ¿
    0.28
    âľª
    0.27
     rog
    0.27
    typings
    0.27
    å·²ç»ıè¾¾åĪ°
    0.26
    åĬ¡
    0.26
    iol
    0.26
    èħ¿
    0.25
     grunt
    0.25
    åĭĻ
    0.24
    Activations Density 2.793%

    No Known Activations