© 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. 56776
    Prev
    Next
    INDEX
    Explanations

    technical context

    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
     Facts
    -0.27
     TNT
    -0.26
    -employed
    -0.25
    lsi
    -0.24
    éĢĦ
    -0.24
    tps
    -0.23
     positioned
    -0.23
    itions
    -0.23
    punkt
    -0.23
     facts
    -0.23
    POSITIVE LOGITS
    enet
    0.34
    åİŁæĸĩ
    0.25
    icro
    0.24
     Entrance
    0.24
    coni
    0.24
    åĸĢ
    0.24
    çĵľ
    0.24
    getView
    0.23
    getMessage
    0.23
    /legal
    0.23
    Activations Density 0.021%

    No Known Activations