© 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. 63463
    Prev
    Next
    INDEX
    Explanations

    code/programming related text

    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
    othermal
    -0.27
    ä¸įçĶ±
    -0.26
     Attribution
    -0.24
    管åĪ¶
    -0.23
    京
    -0.23
    åĬ¡
    -0.23
    ognition
    -0.23
     Whatever
    -0.23
     MP
    -0.23
    -Feb
    -0.23
    POSITIVE LOGITS
    å¨ī
    0.28
    .ids
    0.25
    ç»ĭ
    0.25
    erea
    0.25
     GST
    0.25
    产ä¸ļåıijå±ķ
    0.24
    [ind
    0.24
    管çIJĨå·¥ä½ľ
    0.24
    mina
    0.24
    è¾¹å¢ĥ
    0.24
    Activations Density 3.982%

    No Known Activations