© 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. 129928
    Prev
    Next
    INDEX
    Explanations

    Scientific publications and joy

    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
    itness
    -0.26
    ceptors
    -0.26
    ooky
    -0.26
    æŃ»è§Ĵ
    -0.25
    ä¸Ģåı£
    -0.24
    çŀ°
    -0.24
    çªĿ
    -0.24
    涧
    -0.24
    æĮł
    -0.23
    çĩ¥
    -0.23
    POSITIVE LOGITS
     UIResponder
    0.26
    attended
    0.25
     NC
    0.25
    enc
    0.25
    eph
    0.24
    /arch
    0.24
     fast
    0.24
     multin
    0.23
    ï¸ı
    0.23
    NC
    0.23
    Activations Density 3.249%

    No Known Activations