© 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. 129926
    Prev
    Next
    INDEX
    Explanations

    Technical/Scientific processes

    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
    å°Ĭ
    -0.27
    河水
    -0.26
     Chatt
    -0.25
    çŃ¾åŃĹ
    -0.24
    VISION
    -0.23
    iams
    -0.23
     copyrighted
    -0.23
    åIJįèªī
    -0.22
    éĥ¨éŨ
    -0.22
    owns
    -0.22
    POSITIVE LOGITS
     brace
    0.28
    ">%
    0.27
    odash
    0.27
    еÑģп
    0.26
    essage
    0.26
     Mob
    0.25
    åģľäº§
    0.25
     mob
    0.24
     ion
    0.24
    ron
    0.24
    Activations Density 19.986%

    No Known Activations