© 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. 20-TRANSCODER-HP
    7. 129417
    Prev
    Next
    INDEX
    Explanations

    spirit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.29
    项
    -0.27
    system
    -0.27
    sı
    -0.26
    systems
    -0.26
     íķŃ
    -0.25
    sit
    -0.25
    alo
    -0.25
    edi
    -0.25
     pov
    -0.25
    POSITIVE LOGITS
     merit
    0.26
    à¹Ģà¸ŀลà¸ĩ
    0.25
    æIJ¬å®¶
    0.25
    æľ¬èº«å°±
    0.25
    wap
    0.24
     constructive
    0.24
    åĿļæĮģ以
    0.24
     motivated
    0.24
    -neck
    0.24
     Construct
    0.24
    Activations Density 12.273%

    No Known Activations