© 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. 30412
    Prev
    Next
    INDEX
    Explanations

    colors

    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
    ieties
    -0.27
    å¢ĥ
    -0.27
    plies
    -0.27
    æ·«
    -0.25
    imits
    -0.25
    patches
    -0.25
    ç¼ĺ
    -0.25
    igs
    -0.25
    etic
    -0.25
    çĹĩ
    -0.25
    POSITIVE LOGITS
    賦
    0.30
    æĮ½
    0.28
    æīĭæĦŁ
    0.27
    é¡ı
    0.26
     Shr
    0.25
    èµĭ
    0.25
    /goto
    0.25
    æķĪåĬĽ
    0.24
    åł
    0.24
    Color
    0.24
    Activations Density 4.853%

    No Known Activations