© 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. 22109
    Prev
    Next
    INDEX
    Explanations

    up

    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
    .fhir
    -0.28
    èĻļæŀĦ
    -0.26
    éĶĻ
    -0.26
    APER
    -0.25
    红èī²
    -0.25
     Lanka
    -0.25
    对æĸ¹
    -0.25
    classes
    -0.25
     classmates
    -0.25
    preter
    -0.25
    POSITIVE LOGITS
    åĭĭ
    0.28
     Merkel
    0.27
    为æĬĵ
    0.27
     approving
    0.26
    èĬĤ
    0.26
     brow
    0.25
     Nack
    0.25
    æİĮæı¡äºĨ
    0.25
    /lg
    0.25
    ODO
    0.25
    Activations Density 0.001%

    No Known Activations