© 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. 129465
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     prio
    -0.29
    å¿ħä¸įåı¯
    -0.28
    aben
    -0.27
    交æĺĵä¸Ńå¿ĥ
    -0.26
    .selector
    -0.26
    onis
    -0.25
    éĹ¨æ§Ľ
    -0.25
    )|(
    -0.25
    ecom
    -0.24
     gió
    -0.24
    POSITIVE LOGITS
    (gp
    0.26
    åĨĻäºĨ
    0.24
    iju
    0.24
     cog
    0.24
     зам
    0.24
    ong
    0.23
    åĨĻ
    0.23
    antz
    0.23
    èį¤
    0.23
    hard
    0.23
    Activations Density 3.228%

    No Known Activations

    This feature has no known activations.