© 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. 29827
    Prev
    Next
    INDEX
    Explanations

    pollution

    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
    »¿
    -0.31
    绿èī²
    -0.26
    貨
    -0.25
    RON
    -0.25
    綳
    -0.24
    anut
    -0.24
    olini
    -0.24
     Astros
    -0.24
     ()↵↵
    -0.23
    æºĸ
    -0.23
    POSITIVE LOGITS
    Composition
    0.29
     compositions
    0.28
    InView
    0.26
    磾
    0.25
     calor
    0.25
     composition
    0.25
    ATORY
    0.25
    ev
    0.25
    çľŁäºº
    0.25
    Arr
    0.24
    Activations Density 1.254%

    No Known Activations