© 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. 107802
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    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
    istar
    -0.28
    éĥİ
    -0.28
     hostel
    -0.27
    corp
    -0.26
    .AutoScaleDimensions
    -0.25
     Manifest
    -0.24
    .mk
    -0.24
    äºĭå®ŀ
    -0.23
     wherever
    -0.23
     beaut
    -0.23
    POSITIVE LOGITS
    ential
    0.28
    adio
    0.26
    terior
    0.24
    ä¹ĥ
    0.24
    æĸ¹éĿ¢
    0.24
     ongoing
    0.24
    èĶ¡
    0.24
     upper
    0.24
     neg
    0.23
    ืà¸Ńà¸ĩ
    0.23
    Activations Density 1.334%

    No Known Activations