© 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. 43156
    Prev
    Next
    INDEX
    Explanations

    Foreign languages or code

    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
    éķ¿
    -0.27
    åºĦ
    -0.26
     cl
    -0.24
     Pop
    -0.24
    AGR
    -0.24
    X
    -0.24
    .den
    -0.24
    å¨ij
    -0.24
    åĬ¡
    -0.24
    Pop
    -0.24
    POSITIVE LOGITS
    ä½ĵ
    0.28
    //}}
    0.28
    ç¼°
    0.27
    ort
    0.27
    åĮĹè·¯
    0.27
    orse
    0.27
     ÑĥÑģп
    0.25
     поб
    0.25
    çĬ´
    0.24
    odef
    0.24
    Activations Density 0.002%

    No Known Activations