© 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. 22226
    Prev
    Next
    INDEX
    Explanations

    Medical conditions and disabilities

    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
    tur
    -0.29
    Lifetime
    -0.27
     Turbo
    -0.27
    eful
    -0.27
    TEMP
    -0.27
    åIJįçīĩ
    -0.26
    Variables
    -0.25
    OPTARG
    -0.25
    Tur
    -0.25
    orges
    -0.25
    POSITIVE LOGITS
    æ®ĭçĸ¾
    0.32
    æ®ĭçĸ¾äºº
    0.31
    rias
    0.29
    ias
    0.29
    éļľ
    0.27
    翳
    0.27
     disabilities
    0.27
    .iOS
    0.26
    éļľç¢į
    0.26
    alse
    0.26
    Activations Density 0.010%

    No Known Activations