© 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. 41440
    Prev
    Next
    INDEX
    Explanations

    "com" and "term"

    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
    vol
    -0.31
    è¢Ĵ
    -0.28
    won
    -0.27
    ä¸ĩåIJ¨
    -0.26
    misc
    -0.26
     wedge
    -0.25
     smith
    -0.25
    æ¥Ķ
    -0.25
    åĨ²åĩ»
    -0.25
    illos
    -0.24
    POSITIVE LOGITS
     terminal
    0.33
    Com
    0.33
    å¤ĩ
    0.32
     Com
    0.32
     terminals
    0.31
     regulators
    0.30
    proper
    0.30
     com
    0.29
    terminal
    0.29
    com
    0.29
    Activations Density 0.032%

    No Known Activations