© 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. 22-TRANSCODER-HP
    7. 129474
    Prev
    Next
    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±ħ
    -0.28
     perse
    -0.27
    llib
    -0.27
    ège
    -0.27
     Saturn
    -0.24
    enade
    -0.24
    iciones
    -0.24
    rô
    -0.24
    jom
    -0.23
    _JO
    -0.23
    POSITIVE LOGITS
    çĶ²
    0.28
    -Smith
    0.28
    媾
    0.26
    æĺ¯åIJ¦ä¼ļ
    0.25
    åºIJ
    0.24
    ottenham
    0.24
    tright
    0.24
     nesting
    0.24
     McGr
    0.23
    .exc
    0.23
    Activations Density 0.002%

    No Known Activations