© 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. 141653
    Prev
    Next
    INDEX
    Explanations

    the

    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
    anden
    -0.29
    èģļåIJĪ
    -0.25
    ley
    -0.24
    avage
    -0.24
    Âł
    -0.24
    ot
    -0.24
    æij¸
    -0.24
    ase
    -0.24
    rase
    -0.24
     expression
    -0.23
    POSITIVE LOGITS
    EXIT
    0.28
    æ½ľ
    0.28
    çĮ®
    0.28
    å¯Ħ
    0.26
    çį»
    0.26
     AUX
    0.25
     quarters
    0.25
    ])+
    0.25
    Ļ¨
    0.25
    maal
    0.25
    Activations Density 2.118%

    No Known Activations