© 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. 31-TRANSCODER-HP
    7. 18740
    Prev
    Next
    INDEX
    Explanations

    brain

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĴĹ
    -0.27
    alth
    -0.25
    eut
    -0.24
    uil
    -0.24
    uchs
    -0.24
    Repositories
    -0.24
    eworthy
    -0.23
    tega
    -0.23
    åIJĪåIJĮ
    -0.23
    vy
    -0.23
    POSITIVE LOGITS
    èĦij
    1.32
     brain
    1.29
     Brain
    1.15
    brain
    1.13
    大èĦij
    1.12
    Brain
    1.10
    èħ¦
    1.08
     brains
    1.06
    Brains
    0.91
    brains
    0.87
    Activations Density 14.577%

    No Known Activations