© 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. 8433
    Prev
    Next
    INDEX
    Explanations

    People and experiences

    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
     logical
    -0.56
    éĢ»è¾ij
    -0.56
    çIJĨ
    -0.55
     logic
    -0.50
    _logic
    -0.48
    éģĵçIJĨ
    -0.48
     intuit
    -0.47
     intuitive
    -0.47
    Logical
    -0.46
    logic
    -0.45
    POSITIVE LOGITS
    .fre
    0.28
     Guarantee
    0.25
    è¡Ķ
    0.25
    ooter
    0.25
    alom
    0.24
     Guaranteed
    0.23
    æĴ
    0.23
    饿
    0.23
    illions
    0.23
    ill
    0.23
    Activations Density 0.001%

    No Known Activations