© 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. 98337
    Prev
    Next
    INDEX
    Explanations

    Code/Technical documentation

    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
    apter
    -0.28
    .df
    -0.28
    书æĪ¿
    -0.27
    cedes
    -0.25
    ientos
    -0.25
     Polly
    -0.25
    笥
    -0.25
    ök
    -0.24
    angles
    -0.24
    kit
    -0.24
    POSITIVE LOGITS
    åIJİèĢħ
    0.30
    èĢĮå·²
    0.29
    赶æĿ¥
    0.27
    åĪ°åºķ
    0.25
    åīįèĢħ
    0.24
     Ara
    0.24
    ç´ĢéĮĦ
    0.24
    è¿Ļä¹Īåģļ
    0.24
     om
    0.24
    è¶Ĭ好
    0.23
    Activations Density 0.007%

    No Known Activations