© 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. 18371
    Prev
    Next
    INDEX
    Explanations

    technical writing fragments

    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
    æѧ
    -0.26
     binaries
    -0.25
     cru
    -0.25
    åĿļ
    -0.24
     admissions
    -0.24
     Cru
    -0.24
     nonce
    -0.23
    æĬĺå°Ħ
    -0.23
    代åĬŀ
    -0.23
    objs
    -0.23
    POSITIVE LOGITS
     Mood
    0.27
    èµĦ
    0.27
    å¸ĤæĶ¿åºľ
    0.27
    (Material
    0.25
    pile
    0.25
     material
    0.25
    ifes
    0.25
     mah
    0.24
    /material
    0.24
     mater
    0.24
    Activations Density 0.925%

    No Known Activations