© 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. 22138
    Prev
    Next
    INDEX
    Explanations

    Code snippets/technical data

    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
    Negative Logits
    åĬłæ²¹
    -0.30
     anz
    -0.28
    å¥Ĺ
    -0.27
    ck
    -0.26
    [code
    -0.26
     Äijầy
    -0.26
    åIJ¸å¼ķ
    -0.26
    anz
    -0.26
    å¾·å·ŀ
    -0.25
     ack
    -0.25
    POSITIVE LOGITS
    åł¡
    0.28
    .instructions
    0.27
    CLI
    0.26
    /cgi
    0.26
    emer
    0.25
    parameters
    0.24
    ILI
    0.24
    裱
    0.24
    dale
    0.24
    çĿ
    0.24
    Activations Density 0.015%

    No Known Activations