© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43679
    Prev
    Next
    INDEX
    Explanations

    land and water formations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    京
    -0.31
     qu
    -0.30
    IFI
    -0.25
    erus
    -0.25
    æĥ¯
    -0.25
    iological
    -0.25
    essor
    -0.25
    lus
    -0.25
    _collision
    -0.25
    åĭĴ
    -0.24
    POSITIVE LOGITS
    è¦ĨçĽĸ
    0.35
    -cover
    0.29
    waters
    0.27
    ymb
    0.27
     covering
    0.27
     water
    0.27
    æ°´éĩı
    0.26
     cover
    0.26
     coverage
    0.26
    å¥Ķ
    0.26
    Activations Density 0.003%

    No Known Activations