© 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. 108000
    Prev
    Next
    INDEX
    Explanations

    questions and relationships

    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
    onga
    -0.27
     Libre
    -0.25
     guarante
    -0.25
     grâce
    -0.25
    rels
    -0.24
     Camel
    -0.24
    /////////////////////////////////////////////////////////////////////////////↵
    -0.24
    -properties
    -0.24
    -man
    -0.23
    ä¸ĭä¸Ģ
    -0.23
    POSITIVE LOGITS
    erox
    0.27
    iss
    0.24
     msec
    0.24
     Airways
    0.24
    æĪijæĬĬ
    0.24
     æı
    0.24
     tamp
    0.23
    jet
    0.23
    å°±æĬĬ
    0.23
    +len
    0.23
    Activations Density 22.627%

    No Known Activations