© 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. 18-TRANSCODER-HP
    7. 90016
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    execution
    -0.32
     execution
    -0.28
    Ax
    -0.27
    ï¼Įé»ĺ认
    -0.27
    .execution
    -0.27
    änger
    -0.25
    Execution
    -0.24
     worms
    -0.24
    etsk
    -0.24
    elif
    -0.23
    POSITIVE LOGITS
    FC
    0.27
    fc
    0.25
    åĪĨä¼ļ
    0.25
    æŀ¥
    0.25
    rys
    0.24
    emple
    0.24
    缦
    0.23
    ???↵↵
    0.23
    ++]
    0.23
    ??↵↵
    0.23
    Activations Density 55.734%

    No Known Activations