© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29273
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    Negative Logits
    anza
    -0.29
    oku
    -0.27
    ½Ķ
    -0.25
    å¸Ŀçİĭ
    -0.25
    uers
    -0.25
    è¿ĺéľĢ
    -0.25
    uevo
    -0.25
    .GetEnumerator
    -0.24
    æķħ乡
    -0.24
    秣
    -0.24
    POSITIVE LOGITS
    .INTERNAL
    0.30
    enda
    0.29
    endas
    0.28
    )..
    0.26
    én
    0.26
    adays
    0.26
    JOR
    0.25
    )."
    0.25
    bbe
    0.25
    çĹĩ
    0.25
    Activations Density 2.516%

    No Known Activations