© 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. 30-TRANSCODER-HP
    7. 96351
    Prev
    Next
    INDEX
    Explanations

    code/data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffective
    -0.29
    åĤ¬
    -0.26
    æīĩ
    -0.25
    agal
    -0.24
    tfoot
    -0.24
    ripp
    -0.24
     printed
    -0.23
    婵
    -0.23
    odcast
    -0.23
    çĶŁäº§æĢ»
    -0.23
    POSITIVE LOGITS
    åħĥå®Ŀ
    0.27
     textbooks
    0.27
    TITLE
    0.27
    èıĺ
    0.25
    åħ¨èº«
    0.25
    ä¸įå¾Ĺå·²
    0.25
    /wiki
    0.25
    titles
    0.25
    _operations
    0.24
    æ±²
    0.24
    Activations Density 0.917%

    No Known Activations