© 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. 58208
    Prev
    Next
    INDEX
    Explanations

    choice/decision

    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
    缸è¿ij
    -0.26
    æ½®
    -0.26
    è²Į
    -0.26
    CAPE
    -0.26
    omo
    -0.25
    epam
    -0.25
    .exchange
    -0.25
    eta
    -0.25
    éĩıåĮĸ
    -0.25
    好ä¸į容æĺĵ
    -0.25
    POSITIVE LOGITS
     choices
    0.69
     decisions
    0.61
     Choices
    0.59
    choices
    0.56
     choice
    0.54
    åĨ³çŃĸ
    0.53
    Choices
    0.50
     decision
    0.49
    choice
    0.48
     Choice
    0.47
    Activations Density 0.012%

    No Known Activations