© 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. 18824
    Prev
    Next
    INDEX
    Explanations

    Biology/genetics context

    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
     Open
    -0.32
    open
    -0.31
     open
    -0.31
    Open
    -0.30
    CAPE
    -0.28
     Complex
    -0.28
    -open
    -0.27
    å¼ĢæĶ¾
    -0.27
    AMI
    -0.27
    OPEN
    -0.27
    POSITIVE LOGITS
     REGION
    0.28
    inance
    0.27
    xbd
    0.26
     Rc
    0.26
     ownerId
    0.25
     Rw
    0.25
    reste
    0.24
    修士
    0.24
    mó
    0.24
    èµ·
    0.23
    Activations Density 0.271%

    No Known Activations