© 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. 12-TRANSCODER-HP
    7. 23929
    Prev
    Next
    INDEX
    Explanations

    programming, system administration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gles
    -0.28
     provisions
    -0.27
     embassy
    -0.26
     sleeper
    -0.25
    TestFixture
    -0.25
    idle
    -0.25
    é¢Ħ约
    -0.24
    åĨ²
    -0.24
     çĶŁåij½åij¨æľŁ
    -0.24
    代谢
    -0.23
    POSITIVE LOGITS
    çĶ¨æĪ·æıIJä¾Ľ
    0.26
    coni
    0.26
     getSource
    0.26
    ullo
    0.26
     SOUR
    0.26
     sources
    0.25
     priority
    0.25
    å§ĵ
    0.25
    .getLine
    0.25
    odo
    0.25
    Activations Density 0.002%

    No Known Activations