© 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. 41579
    Prev
    Next
    INDEX
    Explanations

    diverse document and article content

    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
    å¢Ļ
    -0.28
    _trees
    -0.28
    æľ¦èĥ§
    -0.28
    é¥Ńèıľ
    -0.28
    oil
    -0.28
    æ³¼
    -0.27
    ete
    -0.26
    åĻ¬
    -0.26
    foods
    -0.26
    æ²¹
    -0.26
    POSITIVE LOGITS
     raises
    0.29
     raising
    0.29
    çķ¸
    0.29
     factory
    0.29
    -ra
    0.28
     raise
    0.27
    erald
    0.27
    aising
    0.26
     AUD
    0.26
     raised
    0.25
    Activations Density 0.001%

    No Known Activations