© 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. 18548
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     sponsored
    -0.26
    EFR
    -0.26
    ç¶
    -0.25
     churn
    -0.25
    ä¸īæľŁ
    -0.25
    eson
    -0.24
    ivate
    -0.24
    anking
    -0.24
    rollo
    -0.24
     Patreon
    -0.23
    POSITIVE LOGITS
    以æĿ¥
    0.25
    俱
    0.25
    cheon
    0.25
    thin
    0.25
    ugal
    0.24
    åħ¬å¼ı
    0.24
    á»Ńa
    0.24
    ä»Ģä¹Īäºĭ
    0.24
    stylesheet
    0.24
    çĿ¹
    0.23
    Activations Density 0.059%

    No Known Activations

    This feature has no known activations.