© 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. 18918
    Prev
    Next
    INDEX
    Explanations

    interpreting text

    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
    åľ³
    -0.29
    åĪĨ
    -0.29
     consolidation
    -0.28
    j
    -0.27
    åŃĹ
    -0.25
    èļģ
    -0.25
    æĥŃ
    -0.25
    è§Ħæł¼
    -0.25
    示èĮĥ
    -0.25
     acab
    -0.24
    POSITIVE LOGITS
    ius
    0.31
     Inter
    0.31
    Inter
    0.30
    hear
    0.29
    å¹²äºĭ
    0.29
    Means
    0.29
    åIJ¬
    0.28
     getView
    0.28
     view
    0.28
     kijken
    0.27
    Activations Density 0.917%

    No Known Activations