© 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. 63699
    Prev
    Next
    INDEX
    Explanations

    Programming/coding questions

    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
    ç§ij
    -0.31
    ibel
    -0.29
     only
    -0.29
     descriptions
    -0.27
    \"");↵
    -0.26
     roles
    -0.26
    åıª
    -0.26
    -only
    -0.26
     DISCLAIMED
    -0.25
    æİ
    -0.24
    POSITIVE LOGITS
    èľķ
    0.34
    onas
    0.30
    entes
    0.30
     cleans
    0.27
    enty
    0.26
    cket
    0.25
    å¹²åĩĢ
    0.24
    foy
    0.24
    åĨ¤
    0.24
    蹶
    0.24
    Activations Density 83.486%

    No Known Activations