© 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. 29370
    Prev
    Next
    INDEX
    Explanations

    Legal or academic writing

    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
    вл
    -0.27
    hed
    -0.27
    rou
    -0.26
    snap
    -0.26
    ender
    -0.26
    ä¸Ģä½ĵ
    -0.25
    enes
    -0.25
    åľ°åŁŁ
    -0.25
     Option
    -0.24
    rü
    -0.24
    POSITIVE LOGITS
    åij¨è½¬
    0.30
    :///
    0.28
    .$.
    0.25
    ieres
    0.25
    IFORM
    0.24
    ogen
    0.24
    (inner
    0.24
    ä¸Ńåħ³
    0.24
    æĺİçŁ¥
    0.24
    alue
    0.23
    Activations Density 2.325%

    No Known Activations