© 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. 27-TRANSCODER-HP
    7. 9336
    Prev
    Next
    INDEX
    Explanations

    Local community events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     physiology
    -0.28
    &o
    -0.28
    liers
    -0.28
    _character
    -0.27
    èĽĭçĻ½è´¨
    -0.26
    orsi
    -0.26
    主èIJ¥ä¸ļåĬ¡
    -0.26
    lier
    -0.25
    å¤įæŁ¥
    -0.25
    åŀ©
    -0.24
    POSITIVE LOGITS
     organizers
    0.32
     community
    0.29
     crowds
    0.28
     Ahead
    0.27
    OLON
    0.27
     organisers
    0.26
    ANTE
    0.26
     gathering
    0.26
    æ°ijéĹ´
    0.25
    eken
    0.25
    Activations Density 0.005%

    No Known Activations