© 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. 58091
    Prev
    Next
    INDEX
    Explanations

    Website features and descriptions

    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
    pression
    -0.29
     settings
    -0.28
     Veg
    -0.27
    -template
    -0.27
    à¹Īà¸Ń
    -0.26
     Regulation
    -0.26
    atég
    -0.26
     ContentView
    -0.26
    çļĦä¸Ģ项
    -0.26
     registry
    -0.25
    POSITIVE LOGITS
    çī¹ä»·
    0.28
    aby
    0.25
    ä¸ĵå±ŀ
    0.25
    æ¹ĸ
    0.25
    cheap
    0.24
    Easy
    0.24
     Decomp
    0.24
    _easy
    0.24
     concent
    0.24
    éĹ²
    0.24
    Activations Density 0.009%

    No Known Activations