© 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. 23919
    Prev
    Next
    INDEX
    Explanations

    Code files or URLs

    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
    erra
    -0.28
    uv
    -0.28
    erras
    -0.27
    è¿Ļæł·çļĦè¯Ŀ
    -0.27
     testName
    -0.26
    åİĦ
    -0.25
     indication
    -0.25
    ÑĥÑĩа
    -0.25
    ERVICE
    -0.24
    uin
    -0.24
    POSITIVE LOGITS
    OMPI
    0.26
    _integral
    0.24
    åºŀ
    0.24
    à¹Ģà¸Ķ
    0.24
    ampoline
    0.24
    usalem
    0.24
    gable
    0.24
    aily
    0.23
    Tw
    0.23
     _|
    0.23
    Activations Density 0.002%

    No Known Activations